Showing 1–50 of 68 results for author: Lou, W

Path2ST: Hierarchical Cell-Tissue Grounded Cross-Modal Translation for Spatial Transcriptomics

Authors: Ruochen Liu, Wei Lou

Abstract: Predicting spatial gene expression from hematoxylin and eosin (H\&E)-stained images offers a cost-effective alternative to spatial transcriptomics (ST). However, existing methods treat H\&E images as generic visual inputs and ignore their intrinsic biological hierarchy, where spatially organized cell types collectively form functional tissue microenvironments that govern local gene expression prog… ▽ More Predicting spatial gene expression from hematoxylin and eosin (H\&E)-stained images offers a cost-effective alternative to spatial transcriptomics (ST). However, existing methods treat H\&E images as generic visual inputs and ignore their intrinsic biological hierarchy, where spatially organized cell types collectively form functional tissue microenvironments that govern local gene expression programs. To bridge this gap, we formulate H\&E-to-ST prediction as a cross-modal semantic translation task and propose Path2ST, a hierarchically grounded autoregressive framework featuring three key components: (i) a Hierarchical Cell-Tissue Conditioning mechanism that fuses explicit and implicit cellular features with tissue-level semantic representations to construct hierarchical conditioning signals; (ii) a Scale-Adaptive Autoregressive Generation process over a hierarchical semantic vocabulary, enabling coarse-to-fine, biologically consistent expression synthesis; and (iii) SpectraLoss, a full-spectrum objective that jointly enforces ordinal fidelity, models transcriptional bursts, and aligns semantic structures with cell types. Extensive experiments on three datasets demonstrate state-of-the-art performance, validating that Path2ST generates highly accurate and spatially coherent transcriptomic profiles. The related code is released at https://github.com/RuochenLiu23/Path2ST. △ Less

Submitted 11 August, 2026; originally announced August 2026.

Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting

Authors: Haifan Gong, Shiyu Chen, Bodong Wang, Yuqi Wang, Shijie Wang, Guoliang You, Xinyu Xiong, Haowei Wang, Mingzhi Mao, Dexing Kong, Qinghua Liu, Wei Lou, Fei Chen, Guanbin Li

Abstract: Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation and provide limited support for clinical review. We present ThyroidXAgent, a clinician-interactive agentic AI system that coordinates specialized diagnostic tools and stores their outputs as an auditable case-level evidence reco… ▽ More Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation and provide limited support for clinical review. We present ThyroidXAgent, a clinician-interactive agentic AI system that coordinates specialized diagnostic tools and stores their outputs as an auditable case-level evidence record. The system was developed using OpenThyroidDB, a multicentre, multitask resource integrating approximately 0.3 million ultrasound images and 24,000 paired reports, and was evaluated on 28,458 non-overlapping test cases, including 8,721 cases from 35 centres in the private NHC-MISD-TUS cohort. Across heterogeneous datasets, ThyroidXAgent achieved a mean Dice score of 87.21 percent for nodule segmentation and a mean AUROC of 0.9466 for benign-malignant classification. The same workflow supported lymph-node metastasis prediction and follicular versus papillary thyroid carcinoma classification, with AUROCs of 0.864 and 0.805, respectively. For report generation, evidence-grounded assembly outperformed multimodal language-model baselines across three cohorts. ThyClinScore, a lesion-level clinical semantic metric introduced here, showed the strongest correlation with a location-aware language-model judge. ThyroidXAgent improved physician classification accuracy, increased report diagnostic consistency from 70.3 percent to 86.2 percent, and reduced segmentation and reporting time by 35.9 percent and 27.4 percent, respectively. These findings support auditable, clinician-correctable agentic AI for thyroid ultrasound diagnosis and reporting. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Comments: Under review

UnionSparse: An Index-Efficient Sparsity Framework for Low-Bit Sparse LLM Inference on Edge

Authors: Tianhao Jiang, Hang Gu, Teng Wang, Qianyu Cheng, ZhenDong Zheng, Cheng Tang, Qiyue Su, Wenqi Lou, Lei Gong, Chao Wang, Xi Li, Xuehai Zhou

Abstract: Edge LLM inference combines sparsity and low-bit quantization to meet device memory, latency, and power limits. Yet quantization shrinks weight payloads without proportionally reducing sparse metadata, so index traffic and nonzero extraction become critical SpMM bottlenecks. We introduce the Payload-to-Metadata Ratio (PMR) and show that improving PMR raises effective compute intensity in decoding.… ▽ More Edge LLM inference combines sparsity and low-bit quantization to meet device memory, latency, and power limits. Yet quantization shrinks weight payloads without proportionally reducing sparse metadata, so index traffic and nonzero extraction become critical SpMM bottlenecks. We introduce the Payload-to-Metadata Ratio (PMR) and show that improving PMR raises effective compute intensity in decoding. We present UnionSparse, an index-efficient framework that combines Index-Efficient Bitmap Encoding (IE-BME) with a SpMM kernel using Low-Bit Shared-Memory Parallel Decoding (LSPD). IE-BME amortizes metadata and aligns sparse traversal with fragment assembly, while LSPD improves small-batch execution. Under W4A4 quantization and 30%--70% sparsity, UnionSparse outperforms FlashLLM and SpInfer by 2.30x and 1.43x, and CUTLASS and cuBLAS Tensor Core by 1.56x and 3.46x, respectively. These results establish payload-extraction efficiency as a first-order concern for low-bit sparse inference on edge GPUs. Source code is available at: https://github.com/Victor-Alen/UnionSparse. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Comments: 14 pages, 19 figures. Accepted via the ESWEEK 2026 Journal Track for publication in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)

AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions

Authors: Zhiyao Cui, Qianyi Wang, Haoyang Yan, Yiqun Zhang, Siyue Ren, Hangfan Zhang, Zelin Tan, Hao Li, Chunjiang Mu, Dexian Cai, Shao Zhang, Chen Zhang, Meng Li, Jianan Chai, Yuting Fan, Zichao Ye, Xiaolei Yang, Xinyao Lu, Yuyang Yu, Wenjie Lou, Xiaosong Wang, Fenghua Ling, Shiyang Feng, Mao Su, Qiaosheng Zhang , et al. (4 additional authors not shown)

Abstract: Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a single large language model, yet these approaches often expose them to only a limited range of perspectives and directions. We present AgentPanel, a multi-agent forum for human--AI collaboration in scientific exploration.… ▽ More Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a single large language model, yet these approaches often expose them to only a limited range of perspectives and directions. We present AgentPanel, a multi-agent forum for human--AI collaboration in scientific exploration. Heterogeneous agents asynchronously discuss scientific questions in a forum-style environment, while researchers can submit questions, browse and organize candidate ideas, engage agents in follow-up interactions, and optionally generate post-hoc summary reports. We evaluate AgentPanel in terms of idea quality, exploration breadth, interaction effectiveness, candidate-selection efficiency, and practical utility. Offline experiments show that AgentPanel outperforms a centralized multi-agent debate baseline. A human study with 20 participants further shows that users value AgentPanel for perspective diversity and exploration support. In experience-based comparisons with commonly used LLM tools, 65\% of participants favored AgentPanel for both breadth of research directions and overall suitability for early-stage exploration. The platform is publicly available at https://agentpanel.cc/. △ Less

Submitted 4 August, 2026; originally announced August 2026.

SpexPay: A Privacy-Preserving Pay-As-You-Go System for Dynamic Spectrum Sharing

Authors: Mohaimin Al Barat, Hexuan Yu, Shaoyu Li, Yang Xiao, Yi Shi, Eric W. Burger, Y. Thomas Hou, Wenjing Lou

Abstract: Dynamic Spectrum Sharing (DSS) is a cornerstone of next-generation wireless systems, yet existing solutions such as Spectrum Access Systems (SAS) rely on centralized administrators that expose sensitive operational metadata and lack cryptographic transaction accountability. Though SAS administrators, such as Google, have introduced pay-as-you-go pricing models, these approaches still face signific… ▽ More Dynamic Spectrum Sharing (DSS) is a cornerstone of next-generation wireless systems, yet existing solutions such as Spectrum Access Systems (SAS) rely on centralized administrators that expose sensitive operational metadata and lack cryptographic transaction accountability. Though SAS administrators, such as Google, have introduced pay-as-you-go pricing models, these approaches still face significant privacy and accountability challenges as DSS evolves toward a more open and large-scale spectrum marketplace. We present SpexPay, a privacy-preserving and auditable pay-as-you-go spectrum usage framework that enforces fine-grained, usage-linked payments without revealing user identities. Spexpay integrates BBS+ verifiable credentials, unlinkable session pseudonyms, and selective-disclosure proofs to enforce privacy-preserving access authorization, while leveraging Solidity-based smart contracts to realize automated and non-repudiable escrow settlement. By recording only pseudonymous usage evidence and hash-chained metering data on-chain, the system achieves strong unlinkability while preserving verifiable accountability and auditability. A full prototype demonstrates low end-to-end latency ($\approx$150 ms) and modest on-chain cost ($\approx$603K gas or $\approx$\$0.9), showing that SpexPay is practical for real-world DSS deployments. We also evaluated the user-side cryptographic operations on a Raspberry Pi 5 to assess scalability and suitability for edge-class hardware. Our code and artifacts are publicly available at https://github.com/iambarat/SpexPay. △ Less

Submitted 19 July, 2026; originally announced July 2026.

Comments: 20 pages, 2 figures, 3 tables

Realizable N:M Sparse Transformer Inference via Search-Kernel Co-Design

Authors: Yiming Liu, Wenqi Lou, Zhiguang Wang, Zhiwei Ke, Fengrui Zuo, Chao Wang, Xuehai Zhou

Abstract: Vision Transformers (ViTs) achieve strong accuracy but incur high inference latency. Semi-structured N:M sparsity can reduce arithmetic cost, yet its theoretical savings often fail to translate into proportional end-to-end speedups on modern GPUs. This mismatch arises because deployment latency depends not only on arithmetic reduction but also on execution regularity and hardware scheduling under… ▽ More Vision Transformers (ViTs) achieve strong accuracy but incur high inference latency. Semi-structured N:M sparsity can reduce arithmetic cost, yet its theoretical savings often fail to translate into proportional end-to-end speedups on modern GPUs. This mismatch arises because deployment latency depends not only on arithmetic reduction but also on execution regularity and hardware scheduling under sparsity. Achieving practical acceleration, therefore, requires coordinated design across sparse execution and sparsity configuration. To this end, we propose a hardware-software co-design framework for N:M sparse ViT inference. On the hardware side, we design MD-SpMM, an N:M sparse CUDA kernel that reorganizes sparse GEMM into micro-dense, Tensor-Core-aligned dataflow and uses inference-aware adaptive parallelism to sustain utilization. On the software side, we perform layer-wise sparsity search under explicit end-to-end latency budgets using a three-stage heuristic search with constraint relaxation to avoid premature convergence and enable deployment-aware sparsity allocation. Experiments on multiple ViT/Swin models and GPU platforms show that the framework achieves over 2.2x latency speedup while maintaining comparable accuracy and delivering superior accuracy under the same latency constraint. The source code is publicly available at https://github.com/liuganhuo/realizable-nm-sparse-transformer. △ Less

Submitted 14 July, 2026; v1 submitted 14 July, 2026; originally announced July 2026.

Comments: 14 pages, 8 figures, 1 table. Accepted at the 32nd International European Conference on Parallel and Distributed Computing (Euro-Par 2026). Code: https://github.com/liuganhuo/realizable-nm-sparse-transformer

EgoSteer: A Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos

Authors: Yifan Zhong, Zhang Chen, Tianrui Guan, Fanlian Zeng, Yuyao Ye, Tianjia He, Ka Nam Lui, Jiayi Li, Tingrui Zhang, Ruilin Yan, Xinhao Ji, Guangyu Zhao, Wenjie Lou, Jiayuan Zhang, Yuanpei Chen, Yaodong Yang

Abstract: Steerability is a defining capability of generalist robot policies, yet remains largely absent in dexterous-hand systems for lack of large-scale, language-aligned, and action-accurate demonstration data. To address this bottleneck, we present a full-stack system that scales dexterous VLA pre-training from egocentric human videos and enables data-efficient real-robot post-training. It integrates Eg… ▽ More Steerability is a defining capability of generalist robot policies, yet remains largely absent in dexterous-hand systems for lack of large-scale, language-aligned, and action-accurate demonstration data. To address this bottleneck, we present a full-stack system that scales dexterous VLA pre-training from egocentric human videos and enables data-efficient real-robot post-training. It integrates EgoSmith, a data pipeline that curates in-the-wild egocentric videos into 9.6K hours of high-quality pre-training data with 9x higher throughput and better accuracy than prior SOTA; a unified robot stack for teleoperation and human-in-the-loop correction; and EgoSteer, a world-model-enhanced VLA trained on optimized infrastructure. Human-data pre-training equips EgoSteer with language-guided manipulation priors, which are grounded through robot post-training and improved by DAgger refinement. Empirically, EgoSteer robustly executes free-form instructions across 40+ diverse tasks, demonstrating failure recovery, dexterity, and generalization. The pre-trained model also few-shot adapts to complex long-horizon tasks, including box folding, on two embodiments with 75+% success. We open-source the system, data, and model at https://egosteer.github.io/. △ Less

Submitted 21 June, 2026; originally announced July 2026.

A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols

Authors: Yankai Jiang, Weiting Tang, Haoran Sun, Zhenyu Tang, Yuejie Hou, Yingnan Han, Rubo Wang, Yueyuxiao Yang, Cheng Liang, Lilong Wang, Wenjie Lou, Xiaosong Wang, Lei Bai, Meng Yang

Abstract: Autonomous wet-lab experimentation requires more than plausible protocol text: biological intent, quantitative procedures, device constraints and experimental feedback must remain aligned from protocol and SOP design to code and physical execution. We developed ProtoPilot, a self-evolving multi-agent system, together with an expert-grounded benchmark and evaluation framework for testing this conve… ▽ More Autonomous wet-lab experimentation requires more than plausible protocol text: biological intent, quantitative procedures, device constraints and experimental feedback must remain aligned from protocol and SOP design to code and physical execution. We developed ProtoPilot, a self-evolving multi-agent system, together with an expert-grounded benchmark and evaluation framework for testing this conversion as an experimental automation problem. The framework spans 294 synthetic-biology and molecular-biology tasks derived from 98 gold-standard protocols, wet-lab expert rubrics, device-level validity gates and real experimental tests. ProtoPilot incorporates layer-wise verifiability, multi-agent orchestration and a runtime-updated skill library to generate protocols, expand SOPs, synthesize SDK-compliant code and revise workflows from wet-lab feedback. It achieved a Top@3 expert-preference rate of 90.2%, an overall protocol-to-code gate pass rate of 89.5% and an Opentrons pass rate of 88.24%, compared with 32.35% for OpenTrons-AI. Wet-lab validation produced interpretable readouts, Sanger-confirmed products and feedback-corrected PCA-assembled DNA targets, establishing a verifiable route to autonomous experimentation. Together, these results show that the evaluation framework captures execution-relevant requirements for autonomous wet-lab automation, and that ProtoPilot can meet them by converting protocol and code generation into validated execution and feedback-guided revision. △ Less

Submitted 2 July, 2026; v1 submitted 30 June, 2026; originally announced June 2026.

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Authors: Lei Bai, Zongsheng Cao, Yang Chen, Zhiyao Cui, Shangheng Du, Yue Fan, Shiyang Feng, Zijie Guo, Haonan He, Liang He, Xiaohan He, Shuyue Hu, Yusong Hu, Songtao Huang, Yichen Jiang, Hao Li, Xin Li, Dahua Lin, Weihao Lin, Fenghua Ling, Dongrui Liu, Zhuo Liu, Wenjie Lou, Runmin Ma, Chunjiang Mu , et al. (28 additional authors not shown)

Abstract: We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities. To support this goal, we build a long-horizon knowledge-action infrastructure that connects external knowledge, actions,… ▽ More We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities. To support this goal, we build a long-horizon knowledge-action infrastructure that connects external knowledge, actions, observations, and verifier outcomes, producing agentic trajectories with an average length of 45K tokens. Based on this, we train Agents-A1 with a three-stage recipe. First, we perform full-domain supervised fine-tuning to align the base model with broad agentic behaviors. Second, we train domain-level teacher models to capture specialized expertise in each domain. Third, we propose a multi-teacher domain-routed on-policy distillation with salient vocabulary alignment to improve knowledge transfer efficiency across different domains, unifying six heterogeneous domains into one deployable student model. Agents-A1 achieves strong and broad performance for long-horizon agent benchmarks. Compared with 1T-parameter model such as Kimi-K2.6 and DeepSeek-V4-pro, Agents-A1 achieves leading results on SEAL-0 (56.4), IFBench (80.6), HiPhO (46.4), FrontierScience-Olympiad (79.0), and MolBench-Bind (56.8), and remains highly competitive on SciCode (44.3), HLE (47.6) and BrowseComp (75.5). We hope this work provides the community with a practical path for scaling the horizon using a 35B agent that can reach or match the performance of 1T models on long-horizon tasks. △ Less

Submitted 13 July, 2026; v1 submitted 29 June, 2026; originally announced June 2026.

Comments: The model checkpoints and evaluation codebase are available at https://huggingface.co/collections/InternScience/agents-a1 and https://github.com/InternScience/Agents-A1

Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning

Authors: Shanghao Shi, Xiao Wang, Chaoyu Zhang, Hao Li, Wenjing Lou, Thomas Hou, Yevgeniy Vorobeychik, Chongjie Zhang, Ning Zhang

Abstract: The integration of external tools has substantially expanded the capabilities of large language model (LLM) agents, but it also introduces new attack surfaces beyond prompt injection. In particular, cross-tool description poisoning can manipulate planner-visible tool metadata to steer an agent's trajectory, even if the poisoned tool itself is never chosen. To understand the effectiveness of existi… ▽ More The integration of external tools has substantially expanded the capabilities of large language model (LLM) agents, but it also introduces new attack surfaces beyond prompt injection. In particular, cross-tool description poisoning can manipulate planner-visible tool metadata to steer an agent's trajectory, even if the poisoned tool itself is never chosen. To understand the effectiveness of existing defenses against this emerging threat, we first evaluate several prompt-injection defenses and find that they transfer poorly to cross-tool description poisoning. A key observation is that poisoned descriptions persist in the planning context across steps, enabling continuous influence over subsequent tool choices. Building on this insight, we propose Tool-Guard, a novel system-level defense based on a new concept called isolated planning, in which tool invocations that are detected as misaligned or suspicious cause the corresponding tool to be placed in a quarantined list (the influenced list), breaking further influence from poisoned descriptions. With this influence isolated, the tool can continue to be used to support the task, enabling a robust defense that preserves legitimate tool utility. Experiments on the AgentDojo and ASB benchmarks show that Tool-Guard substantially reduces attack success while maintaining high task utility. Our code is available at https://github.com/shishishi123/Tool-Guard. △ Less

Submitted 18 June, 2026; originally announced June 2026.

Comments: Accepted to ICML 2026

From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning

Authors: Shanghao Shi, Chaoyu Zhang, Heng Jin, Yang Xiao, Yevgeniy Vorobeychik, William Yeoh, Ning Zhang, Y. Thomas Hou, Wenjing Lou

Abstract: Federated learning (FL) enables multiple parties to collaboratively fine-tune language models for domain-specific tasks without sharing raw data. Since full model fine-tuning is often prohibitively expensive for FL clients, parameter-efficient fine-tuning (PEFT) has become the de facto approach in practice, freezing the base model and training only a small set of adapters. In this paper, we show t… ▽ More Federated learning (FL) enables multiple parties to collaboratively fine-tune language models for domain-specific tasks without sharing raw data. Since full model fine-tuning is often prohibitively expensive for FL clients, parameter-efficient fine-tuning (PEFT) has become the de facto approach in practice, freezing the base model and training only a small set of adapters. In this paper, we show that a malicious parameter server can stealthily corrupt a PEFT adapter into a privacy backdoor that implicitly memorizes the client's training samples as isolated per-sample parameter updates stored in separate neurons, without degrading model utility. Concretely, our attack, NeuroImprint, assigns a dedicated memorization neuron to each training sample and constrains that each neuron is updated at most once along the local fine-tuning trajectory. This design mitigates both cross-sample collisions and cross-step mixing introduced by large local batches and stateful optimizers (e.g., Adam/AdamW) in language-model fine-tuning. After fine-tuning, the resulting isolated per-sample updates can be analytically inverted in closed form to recover text embeddings, which are then deterministically mapped back to token sequences. To understand the generality of our method, we implemented NeuroImprint on multiple language models (BERT, GPT-2, Qwen2, and Llama3.2) and evaluated it across four fine-tuning datasets spanning diverse domains. The results demonstrate that our attack can reconstruct 59% to 79% of all finetuning samples with high semantic fidelity. △ Less

Submitted 18 June, 2026; originally announced June 2026.

Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization

Authors: Hexuan Yu, Chaoyu Zhang, Heng Jin, Shanghao Shi, Ning Zhang, Y. Thomas Hou, Wenjing Lou

Abstract: Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments. However, many deployments transmit the full UI state to remote inference servers even when most elements are irrelevant to the current task, which can leak sensitive but unnecessary context such as authentication codes, private… ▽ More Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments. However, many deployments transmit the full UI state to remote inference servers even when most elements are irrelevant to the current task, which can leak sensitive but unnecessary context such as authentication codes, private notifications, and background application states. We propose MINIM, a trusted local broker that performs privacy-aware minimization on the client side before any observation leaves the device. Grounded in Contextual Integrity (CI), MINIM learns a dual-score representation for each UI element by predicting an inherent sensitivity score (s) and a task-conditioned necessity score (n). These scores drive a ternary disclosure policy that keeps essential elements, abstracts sensitive attributes when needed, and removes task-irrelevant content. We optimize a CI-aware objective that penalizes necessity errors more strongly on high-risk content, enabling aggressive pruning while preserving task-critical information. Experiments on real-world UI observations derived from WebArena show that MINIM substantially reduces task-irrelevant sensitive leakage while preserving task-critical semantic context and the interactive affordances required for reliable agent actions. △ Less

Submitted 11 June, 2026; originally announced June 2026.

Comments: Accepted at ICML 2026 (43rd International Conference on Machine Learning, Seoul, South Korea). Code available at https://github.com/yyyyhx/MINIM

Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation

Authors: Diandian Gu, Jing Lin, Gaohong Liu, Jiahang Liu, Su Ma, Guang Shi, Jun Wang, Qinlong Wang, Qianyi Wu, Zhongcong Xu, Xuanyu Yi, Zihao Yu, Jianfeng Zhang, Zhuolin Zheng, Yifan Zhu, Rui Chen, Hengkai Guo, Xiaoyang Guo, Mingcong Han, Xu Han, Xiu Li, Yixun Liang, Weiqiang Lou, Junzhe Lu, Guan Luo , et al. (3 additional authors not shown)

Abstract: We present Seed3D 2.0, an advanced 3D content generation system built on Seed3D 1.0, with substantial improvements across generation fidelity, simulation-ready capabilities, and application coverage. For geometry, a coarse-to-fine two-stage pipeline decouples global structure learning from high-frequency detail recovery, while a locality-aware VAE achieves higher spatial compression and more effic… ▽ More We present Seed3D 2.0, an advanced 3D content generation system built on Seed3D 1.0, with substantial improvements across generation fidelity, simulation-ready capabilities, and application coverage. For geometry, a coarse-to-fine two-stage pipeline decouples global structure learning from high-frequency detail recovery, while a locality-aware VAE achieves higher spatial compression and more efficient decoding. For texture and material generation, we replace the cascaded pipeline of Seed3D 1.0 with a unified PBR model that directly generates multi-view albedo and metallic-roughness maps, enhanced by Mixture-of-Experts scaling and VLM-based semantic conditioning for improved material precision and visual fidelity. Beyond single-object generation, Seed3D 2.0 introduces a simulation-ready model suite comprising scene layout planning, part-aware decomposition, and training-free articulation generation, enabling coherent scene construction and part-level physical interaction across physics and graphics engines. A large-scale human preference study against five recent commercial models shows that Seed3D 2.0 achieves consistent win rates of 69.0% to 89.9% in textured 3D asset generation. Seed3D 2.0 is available on https://exp.volcengine.com/ark/vision?_vtm_=0.0.c70961.d701978.0&mode=vision&modelId=doubao-seed3d-2-0-260328&tab=Gen3D △ Less

Submitted 22 April, 2026; originally announced May 2026.

Comments: Seed3D 2.0 Technical Report; Official Page on https://seed.bytedance.com/seed3d_2_0

ARMOR 2025: A Military-Aligned Benchmark for Evaluating Large Language Model Safety Beyond Civilian Contexts

Authors: Sydney Johns, Heng Jin, Chaoyu Zhang, Y. Thomas Hou, Wenjing Lou

Abstract: Large language models (LLMs) are now being explored for defense applications that require reliable and legally compliant decision support. They also hold significant potential to enhance decision making, coordination, and operational efficiency in military contexts. These uses demand evaluation methods that reflect the doctrinal standards that guide real military operations. Existing safety benchm… ▽ More Large language models (LLMs) are now being explored for defense applications that require reliable and legally compliant decision support. They also hold significant potential to enhance decision making, coordination, and operational efficiency in military contexts. These uses demand evaluation methods that reflect the doctrinal standards that guide real military operations. Existing safety benchmarks focus on general social risks and do not test whether models follow the legal and ethical rules that govern real military operations. To address this gap, we introduce ARMOR 2025, a military aligned safety benchmark grounded in three core military doctrines the Law of War, the Rules of Engagement, and the Joint Ethics Regulation. We extract doctrinal text from these sources and generate multiple choice questions that preserve the intended meaning of each rule. The benchmark is organized through a taxonomy informed by the Observe Orient Decide Act (OODA) decision making framework. This structure enables systematic testing of accuracy and refusal across military relevant decision types. This benchmark features a structured 12-category taxonomy, 519 doctrinally grounded prompts, and rigorous evaluation procedures applied to 21 commercial LLMs. Evaluation results reveal critical gaps in safety alignment for military applications. △ Less

Submitted 30 April, 2026; originally announced May 2026.

Uncovering Exotic Paired States in the 2D Spin-Imbalanced Fermi Gas with Neural Wave Functions

Authors: Wan Tong Lou, Gino Cassella, Andres Perez Fadon, Halvard Sutterud, David Pfau, James S. Spencer, Johannes Knolle, W. M. C. Foulkes

Abstract: We study the zero-temperature phase diagram of the 2D spin-imbalanced Fermi gas with short-ranged attractive interactions using the recently developed neural network variational Monte Carlo method with the AGPs FermiNet Ansatz. The Fulde-Ferrell-Larkin-Ovchinnikov phase is observed in the weakly interacting BCS limit and a polarised superfluid is seen in the strongly interacting BEC limit. When th… ▽ More We study the zero-temperature phase diagram of the 2D spin-imbalanced Fermi gas with short-ranged attractive interactions using the recently developed neural network variational Monte Carlo method with the AGPs FermiNet Ansatz. The Fulde-Ferrell-Larkin-Ovchinnikov phase is observed in the weakly interacting BCS limit and a polarised superfluid is seen in the strongly interacting BEC limit. When the interactions are strong, the minority-spin momentum density is reduced almost to zero in the momentum-space region occupied by the unpaired majority-spin electrons. When the interactions are very strong, phase separation occurs, with regions containing bosonic pairs and unpaired regions occupied by the remaining majority-spin particles. In addition, we observe translational symmetry breaking at intermediate interaction strengths, where the system forms an exotic crystal of Cooper pairs in a Fermi fluid of unpaired majority-spin particles. We provide a possible explanation for the formation of the crystalline phase, explain the origins of the k-space momentum-density hole when the pairs are tightly bound, and discuss how our approach opens new directions for future work. △ Less

Submitted 27 April, 2026; originally announced April 2026.

Comments: 23 pages, 17 figures

MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization

Authors: Lisheng Zhang, Lilong Wang, Xiangyu Sun, Wei Tang, Haoyang Su, Yuehui Qian, Qikui Yang, Qingsong Li, Zhenyu Tang, Haoran Sun, Yingnan Han, Yankai Jiang, Wenjie Lou, Bowen Zhou, Xiaosong Wang, Lei Bai, Zhengwei Xie

Abstract: Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specialized tools in multi-step workflows, yet current AI agents struggle to maintain robust performance and consistently underperform in these high-complexity scenarios. Here we present MolClaw, an autonomous agent that leads drug molecule evaluation, scre… ▽ More Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specialized tools in multi-step workflows, yet current AI agents struggle to maintain robust performance and consistently underperform in these high-complexity scenarios. Here we present MolClaw, an autonomous agent that leads drug molecule evaluation, screening, and optimization. It unifies over 30 specialized domain resources through a three-tier hierarchical skill architecture (70 skills in total) that facilitates agent long-term interaction at runtime: tool-level skills standardize atomic operations, workflow-level skills compose them into validated pipelines with quality check and reflection, and a discipline-level skill supplies scientific principles governing planning and verification across all scenarios in the field. Additionally, we introduce MolBench, a benchmark comprising molecular screening, optimization, and end-to-end discovery challenges spanning 8 to 50+ sequential tool calls. MolClaw achieves state-of-the-art performance across all metrics, and ablation studies confirm that gains concentrate on tasks that demand structured workflows while vanishing on those solvable with ad hoc scripting, establishing workflow orchestration competence as the primary capability bottleneck for AI-driven drug discovery. △ Less

Submitted 17 May, 2026; v1 submitted 2 April, 2026; originally announced April 2026.

Comments: 28 pages, 8 figures. Code and data will be released

ClawCoin: An Agentic AI-Native Cryptocurrency for Decentralized Agent Economies

Authors: Shaoyu Li, Chaoyu Zhang, Hexuan Yu, Y. Thomas Hou, Wenjing Lou

Abstract: Autonomous AI agents live or die by the API tokens they consume: without paid inference capacity they cannot reason, act, or delegate. Compute-token cost has become the binding resource of the emerging agent economy, yet it is non-transferable: it is account-bound, vendor-specific, and absent from on-chain ledgers. Existing payment rails such as x402 move fiat-backed value between agents, but they… ▽ More Autonomous AI agents live or die by the API tokens they consume: without paid inference capacity they cannot reason, act, or delegate. Compute-token cost has become the binding resource of the emerging agent economy, yet it is non-transferable: it is account-bound, vendor-specific, and absent from on-chain ledgers. Existing payment rails such as x402 move fiat-backed value between agents, but they do not represent the quantity agents actually burn. As a result, agents can transport purchasing power but cannot quote, escrow, or settle workflows in a unit aligned with compute cost. We present ClawCoin, a tokenized, compute-cost-indexed unit of account and settlement asset for decentralized agent economies. ClawCoin combines four layers: a robust basket index over standardized prices; an oracle publishing signed fresh attestations; a NAV-based mint/redeem vault with coverage thresholds and rate limits; and an on-chain settlement layer for multi-hop delegations. We implement a prototype on an Ethereum-compatible L2 and evaluate it using a multi-agent simulator and the OpenClaw testbed. Across single-agent, multi-agent, workflow, and procurement experiments, ClawCoin stabilizes execution capacity under cost shocks, reduces cross-agent quote dispersion, eliminates partial settlements, and sustains cooperative market dynamics that fiat-denominated baselines cannot. These results suggest that compute-indexed units of account can improve decentralized agent coordination. △ Less

Submitted 20 April, 2026; originally announced April 2026.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI

Authors: Heng Jin, Chaoyu Zhang, Hexuan Yu, Shanghao Shi, Ning Zhang, Y. Thomas Hou, Wenjing Lou

Abstract: Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning and inference are increasingly delegated to cloud providers for simplified deployment and access to proprietary models, yet this creates a fundamental trust gap. Although cryptographic and TEE-based verification approaches exist, prohibitive proving costs a… ▽ More Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning and inference are increasingly delegated to cloud providers for simplified deployment and access to proprietary models, yet this creates a fundamental trust gap. Although cryptographic and TEE-based verification approaches exist, prohibitive proving costs and limited TEE memory prevent them from scaling to modern LLMs, leaving clients unable to practically audit these processes. This lack of transparency creates concrete security risks that can silently compromise service integrity. We present AFTUNE, an auditable and verifiable framework that ensures the computational integrity of cloud-based fine-tuning and inference. AFTUNE incorporates a lightweight recording and spot-check mechanism that produces verifiable traces of execution. These traces enable clients to later audit whether the fine-tuning and inference processes followed the agreed configurations, by verifying sampled execution blocks inside a TEE, each covering only a small portion of the model and the execution trace. Our evaluation shows that AFTUNE adds modest overhead and makes auditing practical for clients. △ Less

Submitted 22 July, 2026; v1 submitted 8 March, 2026; originally announced March 2026.

Hermes: A Unified High-Performance NTT Architecture with Hybrid Dataflow

Authors: Hang Gu, Teng Wang, Qianyu Cheng, Jinao Li, Zhendong Zheng, Lei Gong, Wenqi Lou, Xi Li, Xuehai Zhou

Abstract: Fully Homomorphic Encryption (FHE) relies heavily on the Number Theoretic Transform (NTT), making NTT a major performance bottleneck due to its intensive polynomial computations. Hybrid Homomorphic Encryption (HHE), which integrates arithmetic and logic FHE, further requires support for multiple NTT lengths. However, existing accelerators mainly optimize NTT throughput and do not provide unified s… ▽ More Fully Homomorphic Encryption (FHE) relies heavily on the Number Theoretic Transform (NTT), making NTT a major performance bottleneck due to its intensive polynomial computations. Hybrid Homomorphic Encryption (HHE), which integrates arithmetic and logic FHE, further requires support for multiple NTT lengths. However, existing accelerators mainly optimize NTT throughput and do not provide unified support for HHE. This paper presents Hermes, a unified high-performance NTT architecture based on hybrid dataflow. Hermes exploits parallelism along both temporal and spatial dimensions and incorporates a fully pipelined on-chip computing core. A conflict-free on-chip fragmentation algorithm is introduced to resolve bank conflicts and enable burst HBM access, while an efficient dataflow improves computational intensity through data reuse, reducing bandwidth demand. Experimental results show that Hermes supports multiple NTT lengths and achieves up to 13.6x and 1.3x higher throughput than state-of-the-art GPU and FPGA accelerators, respectively. Our source code is available at https://anonymous.4open.science/r/Hermes_conf-4E6F. △ Less

Submitted 2 March, 2026; originally announced March 2026.

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Authors: Weinan Dai, Hanlin Wu, Qiying Yu, Huan-ang Gao, Jiahao Li, Chengquan Jiang, Weiqiang Lou, Yufan Song, Hongli Yu, Jiaze Chen, Wei-Ying Ma, Ya-Qin Zhang, Jingjing Liu, Mingxuan Wang, Xin Liu, Hao Zhou

Abstract: GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive with compiler-based systems such as torch.compile for CUDA kernel generation. Existing CUDA code generation approaches either rely on training-free refinement or f… ▽ More GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive with compiler-based systems such as torch.compile for CUDA kernel generation. Existing CUDA code generation approaches either rely on training-free refinement or fine-tune models within fixed multi-turn execution-feedback loops, but both paradigms fail to fundamentally improve the model's intrinsic CUDA optimization ability, resulting in limited performance gains. We present CUDA Agent, a large-scale agentic reinforcement learning system that develops CUDA kernel expertise through three components: a scalable data synthesis pipeline, a skill-augmented CUDA development environment with automated verification and profiling to provide reliable reward signals, and reinforcement learning algorithmic techniques enabling stable training. CUDA Agent achieves state-of-the-art results on KernelBench, delivering 100\%, 100\%, and 92\% faster rate over torch.compile on KernelBench Level-1, Level-2, and Level-3 splits, outperforming the strongest proprietary models such as Claude Opus 4.5 and Gemini 3 Pro by about 40\% on the hardest Level-3 setting. △ Less

Submitted 27 February, 2026; originally announced February 2026.

IU-GUARD: Privacy-Preserving Spectrum Coordination for Incumbent Users under Dynamic Spectrum Sharing

Authors: Shaoyu Li, Hexuan Yu, Shanghao Shi, Md Mohaimin Al Barat, Yang Xiao, Y. Thomas Hou, Wenjing Lou

Abstract: With the growing demand for wireless spectrum, dynamic spectrum sharing (DSS) frameworks such as the Citizens Broadband Radio Service (CBRS) have emerged as practical solutions to improve utilization while protecting incumbent users (IUs) such as military radars. However, current incumbent protection mechanisms face critical limitations. The Environmental Sensing Capability (ESC) requires costly s… ▽ More With the growing demand for wireless spectrum, dynamic spectrum sharing (DSS) frameworks such as the Citizens Broadband Radio Service (CBRS) have emerged as practical solutions to improve utilization while protecting incumbent users (IUs) such as military radars. However, current incumbent protection mechanisms face critical limitations. The Environmental Sensing Capability (ESC) requires costly sensor deployments and remains vulnerable to interference and security risks. Alternatively, the Incumbent Informing Capability (IIC) requires IUs to disclose their identities and operational parameters to the Spectrum Coordination System (SCS), creating linkable records that compromise operational privacy and mission secrecy. We propose IU-GUARD, a privacy-preserving spectrum sharing framework that enables IUs to access spectrum without revealing their identities. Leveraging verifiable credentials (VCs) and zero-knowledge proofs (ZKPs), IU-GUARD allows IUs to prove their authorization to the SCS while disclosing only essential operational parameters. This decouples IU identity from spectrum access, prevents cross-request linkage, and mitigates the risk of centralized SCS data leakage. We implement a prototype, and our evaluation shows that IU-GUARD achieves strong privacy guarantees with practical computation and communication overhead, making it suitable for real-time DSS deployment. △ Less

Submitted 11 February, 2026; originally announced February 2026.

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Authors: Shiyang Feng, Runmin Ma, Xiangchao Yan, Yue Fan, Yusong Hu, Songtao Huang, Shuaiyu Zhang, Zongsheng Cao, Tianshuo Peng, Jiakang Yuan, Zijie Guo, Zhijie Zhong, Shangheng Du, Weida Wang, Jinxin Shi, Yuhao Zhou, Xiaohan He, Zhiyin Yu, Fangchen Yu, Qihao Zheng, Jiamin Wu, Mianxin Liu, Chi Zhang, Shaowei Hou, Shuya Li , et al. (32 additional authors not shown)

Abstract: We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architecture composed of three coordinated subsystems for generation, verification, and evolution. These subsystems are supported by foundational capabilities for deep research, solution optimization, and long horizon memory. Th… ▽ More We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architecture composed of three coordinated subsystems for generation, verification, and evolution. These subsystems are supported by foundational capabilities for deep research, solution optimization, and long horizon memory. The architecture allows InternAgent-1.5 to operate continuously across extended discovery cycles while maintaining coherent and improving behavior. It also enables the system to coordinate computational modeling and laboratory experimentation within a single unified system. We evaluate InternAgent-1.5 on scientific reasoning benchmarks such as GAIA, HLE, GPQA, and FrontierScience, and the system achieves leading performance that demonstrates strong foundational capabilities. Beyond these benchmarks, we further assess two categories of discovery tasks. In algorithm discovery tasks, InternAgent-1.5 autonomously designs competitive methods for core machine learning problems. In empirical discovery tasks, it executes complete computational or wet lab experiments and produces scientific findings in earth, life, biological, and physical domains. Overall, these results show that InternAgent-1.5 provides a general and scalable framework for autonomous scientific discovery. △ Less

Submitted 9 February, 2026; originally announced February 2026.

Comments: Code and project page: https://github.com/InternScience/InternAgent

How Disciplinary Partnerships Shape Research Landscape in U.S. Library and Information Science Schools

Authors: Jiangen He, Wen Lou

Abstract: This study provides the first comprehensive empirical mapping of how organizational structures and research portfolios co-occur across U.S. Library and Information Science (LIS) schools. Analyzing 14,705 publications from 1,264 faculty members across 44 institutions (2013--2024), we employ computational methods including word embeddings and topic modeling to identify 16 distinct research themes or… ▽ More This study provides the first comprehensive empirical mapping of how organizational structures and research portfolios co-occur across U.S. Library and Information Science (LIS) schools. Analyzing 14,705 publications from 1,264 faculty members across 44 institutions (2013--2024), we employ computational methods including word embeddings and topic modeling to identify 16 distinct research themes organized into three foundational dimensions: Library and Knowledge Organization (LKO), Human-Centered Technology (HCT), and Computing Systems (CS). Our mixed-method analysis reveals significant differences in research composition across organizational types: Computer-affiliated schools cluster tightly in computationally-intensive research and differ significantly from all other school types, while independent Information schools demonstrate the greatest research diversity. Temporal analysis of LIS schools reveals complex evolutionary dynamics: 51.4% are moving toward HCT, 37.8% toward CS, and 37.8% toward LKO, with many schools simultaneously shifting along multiple dimensions. Contrary to narratives of computational dominance, HCT emerged as LIS's primary growth vector. These patterns challenge assumptions about field fragmentation, revealing structured diversification shaped by but not determined by organizational positioning. The study provides empirical foundations for institutional strategic planning, accreditation policy, and understanding LIS's evolving disciplinary identity amid computational transformation. △ Less

Submitted 28 January, 2026; originally announced January 2026.

Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching

Authors: Fengrui Zuo, Zhiwei Ke, Yiming Liu, Wenqi Lou, Chao Wang, Xuehai Zhou

Abstract: Diffusion language models (DLMs) generate text through iterative denoising, but inference requires full-sequence attention at every iteration, resulting in substantial redundant computation on masked tokens. Block-wise diffusion can reduce this cost, yet it typically relies on retraining and constrained update orders, limiting its direct applicability to pretrained DLMs. Our token-level analysis r… ▽ More Diffusion language models (DLMs) generate text through iterative denoising, but inference requires full-sequence attention at every iteration, resulting in substantial redundant computation on masked tokens. Block-wise diffusion can reduce this cost, yet it typically relies on retraining and constrained update orders, limiting its direct applicability to pretrained DLMs. Our token-level analysis reveals pronounced structural locality in DLM inference. Decoding is driven by a small set of prefix-localized active tokens; the influence of distant undecoded context diminishes rapidly, and decoded tokens exhibit stage-wise temporal stability, enabling reuse of intermediate representations except for a brief post-decode transient. Motivated by these observations, we propose \textbf{\placeholder}\footnote{The source code is available at https://github.com/vhicrgit/Window-Diffusion.}, a window-based token pruning and caching method for inference. We maintain a local computation window that slides rightward as denoising progresses, and partition undecoded tokens into: (i) \textit{active tokens} that are computed online, (ii) \textit{buffer tokens} whose KV states are cached and periodically refreshed, and (iii) \textit{far-field tokens} that are pruned outside the window. Computation is restricted to active and buffer tokens within the window, while far-field tokens are omitted at each stage. Experiments on LLaDA and Dream show that, under matched compute budgets, our method achieves up to $99\times$ inference speedup while largely preserving generation performance. △ Less

Submitted 1 February, 2026; v1 submitted 28 January, 2026; originally announced January 2026.

Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle

Authors: Zihan Wang, Cheng Tang, Lei Gong, Cheng Li, Chao Wang, teng wang, Wenqi Lou, Xuehai Zhou

Abstract: Chain-of-Thought (CoT) reasoning in large language models (LLMs) significantly improves accuracy on complex tasks, yet incurs excessive memory overhead due to the long think-stage sequences stored in the Key-Value (KV) cache. Unlike traditional generation tasks where all tokens are uniformly important, CoT emphasizes the final answer, rendering conventional KV compression strategies ineffective. I… ▽ More Chain-of-Thought (CoT) reasoning in large language models (LLMs) significantly improves accuracy on complex tasks, yet incurs excessive memory overhead due to the long think-stage sequences stored in the Key-Value (KV) cache. Unlike traditional generation tasks where all tokens are uniformly important, CoT emphasizes the final answer, rendering conventional KV compression strategies ineffective. In this paper, we present Crystal-KV, an efficient KV cache management framework tailored for CoT reasoning. Our key insight is the answer-first principle. By mapping answer preferences into think-stage attention map, we distinguish between SlipKV, which mainly maintains the reasoning flow but may occasionally introduce misleading context, and CrystalKV, which truly contributes to the correctness of the final answer. Next, we propose an attention-based Least Recently Frequently Used algorithm. It precisely identifies when a SlipKV entry's utility expires and evicts it, retaining CrystalKV without disrupting reasoning flow. Finally, we introduce an adaptive cache budget allocation algorithm. Based on the dynamic proportion of CrystalKV, it estimates the importance of each layer/head and adjusts the KV cache budget during inference, amplifying critical components to improve budget utilization. Results show that Crystal-KV achieves state-of-the-art KV cache compression, significantly improves throughput, and enables faster response time, while maintaining, or even improving, answer accuracy for CoT reasoning. △ Less

Submitted 5 January, 2026; originally announced January 2026.

FC-GUARD: Enabling Anonymous yet Compliant Fiat-to-Cryptocurrency Exchanges

Authors: Shaoyu Li, Hexuan Yu, Md Mohaimin Al Barat, Yang Xiao, Y. Thomas Hou, Wenjing Lou

Abstract: With the rise of decentralized finance, fiat-to-cryptocurrency exchange platforms have become popular entry points into the cryptocurrency ecosystem. However, these platforms frequently fail to ensure adequate privacy protection, as evidenced by real-world breaches that exposed personally identifiable information (PII) and crypto addresses. Such leaks enable adversaries to link real-world identiti… ▽ More With the rise of decentralized finance, fiat-to-cryptocurrency exchange platforms have become popular entry points into the cryptocurrency ecosystem. However, these platforms frequently fail to ensure adequate privacy protection, as evidenced by real-world breaches that exposed personally identifiable information (PII) and crypto addresses. Such leaks enable adversaries to link real-world identities to cryptocurrency transactions, undermining the presumed anonymity of cryptocurrency use. We propose FC-GUARD, a privacy-preserving exchange system designed to preserve user anonymity without compromising regulatory compliance in the exchange of fiat currency for cryptocurrencies. Leveraging verifiable credentials and zero-knowledge proof techniques, FC-GUARD enables fiat-to-cryptocurrency exchanges without revealing users' PII or fiat account details. This breaks the linkage between users' real-world identities and their cryptocurrency addresses, thereby upholding anonymity, a fundamental expectation in the cryptocurrency ecosystem. In addition, FC-GUARD complies with key regulations over cryptocurrency usage, such as know-your-customer requirements and auditability for tax reporting obligations by integrating a lawful de-anonymization mechanism that allows the auditing authority to identify misbehaving users. This ensures regulatory compliance while defaulting to privacy protection. We implement our system on both desktop and mobile platforms, and our evaluation shows its feasibility for practical deployment. △ Less

Submitted 22 January, 2026; originally announced January 2026.

Comments: 10 pages

Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning

Authors: Jiaxuan Lu, Ziyu Kong, Yemin Wang, Rong Fu, Haiyuan Wan, Cheng Yang, Wenjie Lou, Haoran Sun, Lilong Wang, Yankai Jiang, Xiaosong Wang, Xiao Sun, Dongzhan Zhou

Abstract: The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on static, pre-defined tool libraries, a paradigm that fundamentally fails in scientific domains where tools are sparse, heterogeneous, and intrinsically incomplete. In this paper, we propose Test-Time Tool Evolution (TTE)… ▽ More The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on static, pre-defined tool libraries, a paradigm that fundamentally fails in scientific domains where tools are sparse, heterogeneous, and intrinsically incomplete. In this paper, we propose Test-Time Tool Evolution (TTE), a new paradigm that enables agents to synthesize, verify, and evolve executable tools during inference. By transforming tools from fixed resources into problem-driven artifacts, TTE overcomes the rigidity and long-tail limitations of static tool libraries. To facilitate rigorous evaluation, we introduce SciEvo, a benchmark comprising 1,590 scientific reasoning tasks supported by 925 automatically evolved tools. Extensive experiments show that TTE achieves state-of-the-art performance in both accuracy and tool efficiency, while enabling effective cross-domain adaptation of computational tools. The code and benchmark have been released at https://github.com/lujiaxuan0520/Test-Time-Tool-Evol. △ Less

Submitted 12 January, 2026; originally announced January 2026.

Global Inequalities in Clinical Trials Participation

Authors: Wen Lou, Adrián A. Díaz-Faes, Jiangen He, Zhihao Liu, Vincent Larivière

Abstract: Clinical trials are fundamental to the production of medical evidence and determine who gains access to experimental therapies. Although prior work has long documented inequalities in global clinical trial participation, a systematic quantification of the relative contributions of country-level factors and disease burden remains absent. This paper analyzes inequality in participation across 78,117… ▽ More Clinical trials are fundamental to the production of medical evidence and determine who gains access to experimental therapies. Although prior work has long documented inequalities in global clinical trial participation, a systematic quantification of the relative contributions of country-level factors and disease burden remains absent. This paper analyzes inequality in participation across 78,117 randomized controlled trials (RCTs) spanning 16 major disease categories from 2000 to 2024. Linking 185.6 million RCTs participants to country-level disease burden, the paper shows that inequalities in RCTs participation are predominantly explained by country-level factors rather than disease burden. Country-level factors account for 88.9% of the variation in participation, whereas disease and temporal effects contribute marginally. Removing entire disease categories, including those traditionally underfunded, has little effect on overall inequality. Instead, participation is highly concentrated geographically, with a small group of Global North countries enrolling a disproportionate share of participants across nearly all diseases. These patterns persist despite decades of disease-targeted funding and increasing alignment between research efforts and disease burden. Findings also show that without parallel horizontal investments in research capacity, health infrastructure, and governance, even well-funded disease programs are insufficient to reduce inequality in clinical trial participation. △ Less

Submitted 4 August, 2026; v1 submitted 8 January, 2026; originally announced January 2026.

SCP: Accelerating Discovery with a Global Web of Autonomous Scientific Agents

Authors: Yankai Jiang, Wenjie Lou, Lilong Wang, Zhenyu Tang, Shiyang Feng, Jiaxuan Lu, Haoran Sun, Yaning Pan, Shuang Gu, Haoyang Su, Feng Liu, Wangxu Wei, Pan Tan, Dongzhan Zhou, Fenghua Ling, Cheng Tan, Bo Zhang, Xiaosong Wang, Lei Bai, Bowen Zhou

Abstract: We introduce SCP: the Science Context Protocol, an open-source standard designed to accelerate discovery by enabling a global network of autonomous scientific agents. SCP is built on two foundational pillars: (1) Unified Resource Integration: At its core, SCP provides a universal specification for describing and invoking scientific resources, spanning software tools, models, datasets, and physical… ▽ More We introduce SCP: the Science Context Protocol, an open-source standard designed to accelerate discovery by enabling a global network of autonomous scientific agents. SCP is built on two foundational pillars: (1) Unified Resource Integration: At its core, SCP provides a universal specification for describing and invoking scientific resources, spanning software tools, models, datasets, and physical instruments. This protocol-level standardization enables AI agents and applications to discover, call, and compose capabilities seamlessly across disparate platforms and institutional boundaries. (2) Orchestrated Experiment Lifecycle Management: SCP complements the protocol with a secure service architecture, which comprises a centralized SCP Hub and federated SCP Servers. This architecture manages the complete experiment lifecycle (registration, planning, execution, monitoring, and archival), enforces fine-grained authentication and authorization, and orchestrates traceable, end-to-end workflows that bridge computational and physical laboratories. Based on SCP, we have constructed a scientific discovery platform that offers researchers and agents a large-scale ecosystem of more than 1,600 tool resources. Across diverse use cases, SCP facilitates secure, large-scale collaboration between heterogeneous AI systems and human researchers while significantly reducing integration overhead and enhancing reproducibility. By standardizing scientific context and tool orchestration at the protocol level, SCP establishes essential infrastructure for scalable, multi-institution, agent-driven science. △ Less

Submitted 30 December, 2025; originally announced December 2025.

ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge

Authors: Yuntao Dai, Hang Gu, Teng Wang, Qianyu Cheng, Yifei Zheng, Zhiyong Qiu, Lei Gong, Wenqi Lou, Xuehai Zhou

Abstract: Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control, enabling emergent generalization and long-horizon task execution. However, their deployment in dynamic, real-world environments is severely hin dered by high inference latency. While smooth robotic interaction requires control frequencies of 20 to 30 Hz, current VLA models typi cally operate… ▽ More Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control, enabling emergent generalization and long-horizon task execution. However, their deployment in dynamic, real-world environments is severely hin dered by high inference latency. While smooth robotic interaction requires control frequencies of 20 to 30 Hz, current VLA models typi cally operate at only 3-5 Hz on edge devices due to the memory bound nature of autoregressive decoding. Existing optimizations often require extensive retraining or compromise model accuracy. To bridge this gap, we introduce ActionFlow, a system-level inference framework tailored for resource-constrained edge plat forms. At the core of ActionFlow is a Cross-Request Pipelin ing strategy, a novel scheduler that redefines VLA inference as a macro-pipeline of micro-requests. The strategy intelligently batches memory-bound Decode phases with compute-bound Prefill phases across continuous time steps to maximize hardware utilization. Furthermore, to support this scheduling, we propose a Cross Request State Packed Forward operator and a Unified KV Ring Buffer, which fuse fragmented memory operations into efficient dense computations. Experimental results demonstrate that ActionFlow achieves a 2.55x improvement in FPS on the OpenVLA-7B model without retraining, enabling real-time dy namic manipulation on edge hardware. Our work is available at https://anonymous.4open.science/r/ActionFlow-1D47. △ Less

Submitted 23 December, 2025; originally announced December 2025.

Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets

Authors: Jiashi Feng, Xiu Li, Jing Lin, Jiahang Liu, Gaohong Liu, Weiqiang Lou, Su Ma, Guang Shi, Qinlong Wang, Jun Wang, Zhongcong Xu, Xuanyu Yi, Zihao Yu, Jianfeng Zhang, Yifan Zhu, Rui Chen, Jinxin Chi, Zixian Du, Li Han, Lixin Huang, Kaihua Jiang, Yuhan Li, Guan Luo, Shuguang Wang, Qianyi Wu , et al. (3 additional authors not shown)

Abstract: Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face distinct limitations: video-based methods generate diverse content but lack real-time physics feedback for interactive learning, while physics-based engines provide accurate dynamics but face scalability limitations from cos… ▽ More Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face distinct limitations: video-based methods generate diverse content but lack real-time physics feedback for interactive learning, while physics-based engines provide accurate dynamics but face scalability limitations from costly manual asset creation. We present Seed3D 1.0, a foundation model that generates simulation-ready 3D assets from single images, addressing the scalability challenge while maintaining physics rigor. Unlike existing 3D generation models, our system produces assets with accurate geometry, well-aligned textures, and realistic physically-based materials. These assets can be directly integrated into physics engines with minimal configuration, enabling deployment in robotic manipulation and simulation training. Beyond individual objects, the system scales to complete scene generation through assembling objects into coherent environments. By enabling scalable simulation-ready content creation, Seed3D 1.0 provides a foundation for advancing physics-based world simulators. Seed3D 1.0 is now available on https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?modelId=doubao-seed3d-1-0-250928&tab=Gen3D △ Less

Submitted 22 October, 2025; originally announced October 2025.

Comments: Seed3D 1.0 Technical Report; Official Page on https://seed.bytedance.com/seed3d

Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward Mechanism

Authors: Haoran Sun, Yankai Jiang, Zhenyu Tang, Yaning Pan, Shuang Gu, Zekai Lin, Lilong Wang, Wenjie Lou, Lei Liu, Lei Bai, Xiaosong Wang

Abstract: The foundation of reproducible science lies in protocols that are precise, logically ordered, and executable. The autonomous generation of these protocols through natural language queries could greatly improve the efficiency of the reproduction process. However, current leading large language models (LLMs) often generate incomplete or inconsistent protocols, limiting their utility. To address this… ▽ More The foundation of reproducible science lies in protocols that are precise, logically ordered, and executable. The autonomous generation of these protocols through natural language queries could greatly improve the efficiency of the reproduction process. However, current leading large language models (LLMs) often generate incomplete or inconsistent protocols, limiting their utility. To address this limitation, we first introduce SciRecipe, a large-scale dataset of over 12K structured protocols spanning 27 biological subfields and encompassing both comprehension and problem-solving tasks. To further improve protocol generation, we propose the "Sketch-and-Fill" paradigm, which separates analysis, structuring, and expression to ensure each step is explicit and verifiable. Complementing this, the structured component-based reward mechanism evaluates step granularity, action order, and semantic fidelity, aligning model optimization with experimental reliability. Building on these components, we develop Thoth, trained through a staged Knowledge-to-Action process that progresses from knowledge acquisition to operational reasoning and ultimately to robust, executable protocol generation. Across multiple benchmarks, Thoth consistently surpasses both proprietary and open-source LLMs, achieving significant improvements in step alignment, logical sequencing, and semantic accuracy. Our approach paves the way for reliable scientific assistants that bridge knowledge with experimental execution. All data, code, and models will be released publicly. △ Less

Submitted 27 January, 2026; v1 submitted 17 October, 2025; originally announced October 2025.

Robust LLM Training Infrastructure at ByteDance

Authors: Borui Wan, Gaohong Liu, Zuquan Song, Jun Wang, Yun Zhang, Guangming Sheng, Shuguang Wang, Houmin Wei, Chenyuan Wang, Weiqiang Lou, Xi Yang, Mofan Zhang, Kaihua Jiang, Cheng Ren, Xiaoyun Zhi, Menghan Yu, Zhe Nan, Zhuolin Zheng, Baoquan Zhong, Qinlong Wang, Huan Yu, Jinxin Chi, Wang Zhang, Yuhan Li, Zixian Du , et al. (10 additional authors not shown)

Abstract: The training scale of large language models (LLMs) has reached tens of thousands of GPUs and is still continuously expanding, enabling faster learning of larger models. Accompanying the expansion of the resource scale is the prevalence of failures (CUDA error, NaN values, job hang, etc.), which poses significant challenges to training stability. Any large-scale LLM training infrastructure should s… ▽ More The training scale of large language models (LLMs) has reached tens of thousands of GPUs and is still continuously expanding, enabling faster learning of larger models. Accompanying the expansion of the resource scale is the prevalence of failures (CUDA error, NaN values, job hang, etc.), which poses significant challenges to training stability. Any large-scale LLM training infrastructure should strive for minimal training interruption, efficient fault diagnosis, and effective failure tolerance to enable highly efficient continuous training. This paper presents ByteRobust, a large-scale GPU infrastructure management system tailored for robust and stable training of LLMs. It exploits the uniqueness of LLM training process and gives top priorities to detecting and recovering failures in a routine manner. Leveraging parallelisms and characteristics of LLM training, ByteRobust enables high-capacity fault tolerance, prompt fault demarcation, and localization with an effective data-driven approach, comprehensively ensuring continuous and efficient training of LLM tasks. ByteRobust is deployed on a production GPU platform and achieves 97% ETTR for a three-month training job on 9,600 GPUs. △ Less

Submitted 20 October, 2025; v1 submitted 19 September, 2025; originally announced September 2025.

Closing the Visibility Gap: A Monitoring Framework for Verifiable Open RAN Operations

Authors: Hexuan Yu, Md Mohaimin Al Barat, Yang Xiao, Y. Thomas Hou, Wenjing Lou

Abstract: Open Radio Access Network (Open RAN) is reshaping mobile network architecture by promoting openness, disaggregation, and cross-vendor interoperability. However, this architectural flexibility introduces new security challenges, especially in deployments where multiple mobile network operators (MNOs) jointly operate shared components. Existing Zero Trust Architectures (ZTA) in O-RAN, as defined by… ▽ More Open Radio Access Network (Open RAN) is reshaping mobile network architecture by promoting openness, disaggregation, and cross-vendor interoperability. However, this architectural flexibility introduces new security challenges, especially in deployments where multiple mobile network operators (MNOs) jointly operate shared components. Existing Zero Trust Architectures (ZTA) in O-RAN, as defined by governmental and industry standards, implicitly assume that authenticated components will comply with operational policies. However, this assumption creates a critical blind spot: misconfigured or compromised components can silently violate policies, misuse resources, or corrupt downstream processes (e.g., ML-based RIC xApps). To address this critical gap, we propose a monitoring framework for low-trust O-RAN environments that proactively verifies configuration state and control behavior against tenant-defined policies. Our system provides scalable, verifiable oversight to enhance transparency and trust in O-RAN operations. We implement and evaluate the framework using standardized O-RAN configurations, with total processing latency of approximately 200 ms, demonstrating its efficiency and practicality for timely policy enforcement and compliance auditing in multi-MNO deployments. △ Less

Submitted 3 September, 2025; originally announced September 2025.

Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats

Authors: Chaoyu Zhang, Heng Jin, Shanghao Shi, Hexuan Yu, Sydney Johns, Y. Thomas Hou, Wenjing Lou

Abstract: Federated Learning (FL) has gained significant attention for its privacy-preserving capabilities, enabling distributed devices to collaboratively train a global model without sharing raw data. However, its distributed nature forces the central server to blindly trust the local training process and aggregate uncertain model updates, making it susceptible to Byzantine attacks from malicious particip… ▽ More Federated Learning (FL) has gained significant attention for its privacy-preserving capabilities, enabling distributed devices to collaboratively train a global model without sharing raw data. However, its distributed nature forces the central server to blindly trust the local training process and aggregate uncertain model updates, making it susceptible to Byzantine attacks from malicious participants, especially in mission-critical scenarios. Detecting such attacks is challenging due to the diverse knowledge across clients, where variations in model updates may stem from benign factors, such as non-IID data, rather than adversarial behavior. Existing data-driven defenses struggle to distinguish malicious updates from natural variations, leading to high false positive rates and poor filtering performance. To address this challenge, we propose Sentinel, a remote attestation (RA)-based scheme for FL systems that regains client-side transparency and mitigates Byzantine attacks from a system security perspective. Our system employs code instrumentation to track control-flow and monitor critical variables in the local training process. Additionally, we utilize a trusted training recorder within a Trusted Execution Environment (TEE) to generate an attestation report, which is cryptographically signed and securely transmitted to the server. Upon verification, the server ensures that legitimate client training processes remain free from program behavior violation or data manipulation, allowing only trusted model updates to be aggregated into the global model. Experimental results on IoT devices demonstrate that Sentinel ensures the trustworthiness of the local training integrity with low runtime and memory overhead. △ Less

Submitted 30 August, 2025; originally announced September 2025.

Temporal Misalignment Attacks against Multimodal Perception in Autonomous Driving

Authors: Md Hasan Shahriar, Md Mohaimin Al Barat, Harshavardhan Sundar, Ning Zhang, Naren Ramakrishnan, Y. Thomas Hou, Wenjing Lou

Abstract: Multimodal fusion (MMF) plays a critical role in the perception of autonomous driving, which primarily fuses camera and LiDAR streams for a comprehensive and efficient scene understanding. However, its strict reliance on precise temporal synchronization exposes it to new vulnerabilities. In this paper, we introduce DejaVu, an attack that exploits the in-vehicular network to manipulate the integrit… ▽ More Multimodal fusion (MMF) plays a critical role in the perception of autonomous driving, which primarily fuses camera and LiDAR streams for a comprehensive and efficient scene understanding. However, its strict reliance on precise temporal synchronization exposes it to new vulnerabilities. In this paper, we introduce DejaVu, an attack that exploits the in-vehicular network to manipulate the integrity of time and create subtle temporal misalignments, severely degrading downstream MMF-based perception tasks. Our comprehensive attack analysis across different models and datasets reveals the sensors' task-specific imbalanced sensitivities: object detection is overly dependent on LiDAR inputs, while object tracking is highly reliant on the camera inputs. Consequently, with a single-frame LiDAR delay, an attacker can reduce the car detection mAP by up to 88.5%, while with a three-frame camera delay, multiple object tracking accuracy (MOTA) for car drops by 73%. We further demonstrated two attack scenarios using an automotive Ethernet testbed for hardware-in-the-loop validation and the Autoware stack for end-to-end AD simulation, demonstrating the feasibility of the DejaVu attack and its severe impact, such as collisions and phantom braking. Our code and artifacts are publicly available at: https://github.com/shahriar0651/DejaVu. △ Less

Submitted 5 March, 2026; v1 submitted 11 July, 2025; originally announced July 2025.

Comments: 19 pages, 18 Figures

Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search

Authors: Haoran Sun, Yankai Jiang, Wenjie Lou, Yujie Zhang, Wenjie Li, Lilong Wang, Mianxin Liu, Lei Liu, Xiaosong Wang

Abstract: Multimodal large language models (MLLMs) have begun to demonstrate robust reasoning capabilities on general tasks, yet their application in the medical domain remains in its early stages. Constructing chain-of-thought (CoT) training data is essential for bolstering the reasoning abilities of medical MLLMs. However, existing approaches exhibit a deficiency in offering a comprehensive framework for… ▽ More Multimodal large language models (MLLMs) have begun to demonstrate robust reasoning capabilities on general tasks, yet their application in the medical domain remains in its early stages. Constructing chain-of-thought (CoT) training data is essential for bolstering the reasoning abilities of medical MLLMs. However, existing approaches exhibit a deficiency in offering a comprehensive framework for searching and evaluating effective reasoning paths towards critical diagnosis. To address this challenge, we propose Mentor-Intern Collaborative Search (MICS), a novel reasoning-path searching scheme to generate rigorous and effective medical CoT data. MICS first leverages mentor models to initialize the reasoning, one step at a time, then prompts each intern model to continue the thinking along those initiated paths, and finally selects the optimal reasoning path according to the overall reasoning performance of multiple intern models. The reasoning performance is determined by an MICS-Score, which assesses the quality of generated reasoning paths. Eventually, we construct MMRP, a multi-task medical reasoning dataset with ranked difficulty, and Chiron-o1, a new medical MLLM devised via a curriculum learning strategy, with robust visual question-answering and generalizable reasoning capabilities. Extensive experiments demonstrate that Chiron-o1, trained on our CoT dataset constructed using MICS, achieves state-of-the-art performance across a list of medical visual question answering and reasoning benchmarks. Codes are available at https://github.com/manglu097/Chiron-o1 △ Less

Submitted 22 October, 2025; v1 submitted 20 June, 2025; originally announced June 2025.

CoQMoE: Co-Designed Quantization and Computation Orchestration for Mixture-of-Experts Vision Transformer on FPGA

Authors: Jiale Dong, Hao Wu, Zihao Wang, Wenqi Lou, Zhendong Zheng, Lei Gong, Chao Wang, Xuehai Zhou

Abstract: Vision Transformers (ViTs) exhibit superior performance in computer vision tasks but face deployment challenges on resource-constrained devices due to high computational/memory demands. While Mixture-of-Experts Vision Transformers (MoE-ViTs) mitigate this through a scalable architecture with sub-linear computational growth, their hardware implementation on FPGAs remains constrained by resource lim… ▽ More Vision Transformers (ViTs) exhibit superior performance in computer vision tasks but face deployment challenges on resource-constrained devices due to high computational/memory demands. While Mixture-of-Experts Vision Transformers (MoE-ViTs) mitigate this through a scalable architecture with sub-linear computational growth, their hardware implementation on FPGAs remains constrained by resource limitations. This paper proposes a novel accelerator for efficiently implementing quantized MoE models on FPGAs through two key innovations: (1) A dual-stage quantization scheme combining precision-preserving complex quantizers with hardware-friendly simplified quantizers via scale reparameterization, with only 0.28 $\%$ accuracy loss compared to full precision; (2) A resource-aware accelerator architecture featuring latency-optimized streaming attention kernels and reusable linear operators, effectively balancing performance and resource consumption. Experimental results demonstrate that our accelerator achieves nearly 155 frames per second, a 5.35$\times$ improvement in throughput, and over $80\%$ energy reduction compared to state-of-the-art (SOTA) FPGA MoE accelerators, while maintaining $<1\%$ accuracy loss across vision benchmarks. Our implementation is available at https://github.com/DJ000011/CoQMoE. △ Less

Submitted 10 June, 2025; originally announced June 2025.

Comments: Accepted by Euro-Par 2025 (oral)

EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models

Authors: Han Liu, Ruoyao Wen, Srijith Nair, Jia Liu, Wenjing Lou, Chongjie Zhang, William Yeoh, Yevgeniy Vorobeychik, Ning Zhang

Abstract: To address data locality and privacy restrictions, Federated Learning (FL) has recently been adopted to fine-tune large language models (LLMs), enabling improved performance on various downstream tasks without requiring aggregated data. However, the repeated exchange of model updates in FL can result in prohibitively high communication costs, hindering the distributed learning process. To addres… ▽ More To address data locality and privacy restrictions, Federated Learning (FL) has recently been adopted to fine-tune large language models (LLMs), enabling improved performance on various downstream tasks without requiring aggregated data. However, the repeated exchange of model updates in FL can result in prohibitively high communication costs, hindering the distributed learning process. To address this challenge, we propose EcoLoRA, a novel communication-efficient federated fine-tuning framework for LLMs. Leveraging the modular structure, we propose a round-robin segment sharing scheme, where each client uploads only a complementary LoRA segment per round to reduce network bandwidth. It is further combined with adaptive sparsification methods tailored to LoRA's training dynamics and lossless encoding techniques. We conduct extensive evaluations on both question-answering and value-alignment tasks across multiple datasets and models. The results show that EcoLoRA significantly reduces communication overhead without compromising performance. For instance, it reduces communication time by up to 79% and total training time by up to 65%. △ Less

Submitted 10 November, 2025; v1 submitted 20 May, 2025; originally announced June 2025.

Cyrus+: A DRL-based Puncturing Solution to URLLC/eMBB Multiplexing in O-RAN

Authors: Ehsan Ghoreishi, Bahman Abolhassani, Yan Huang, Shiva Acharya, Wenjing Lou, Y. Thomas Hou

Abstract: Puncturing is a promising technique in 3GPP to multiplex Enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low Latency Communications (URLLC) traffic on the same 5G New Radio (NR) air interface. The essence of puncturing is to transmit URLLC packets on demand upon their arrival, by preempting the radio resources (or subcarriers) that are already allocated to eMBB traffic. Although it is consider… ▽ More Puncturing is a promising technique in 3GPP to multiplex Enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low Latency Communications (URLLC) traffic on the same 5G New Radio (NR) air interface. The essence of puncturing is to transmit URLLC packets on demand upon their arrival, by preempting the radio resources (or subcarriers) that are already allocated to eMBB traffic. Although it is considered most bandwidth efficient, puncturing URLLC data on eMBB can lead to degradation of eMBB's performance. Most of the state-of-the-art research addressing this problem employ raw eMBB data throughput as performance metric. This is inadequate as, after puncturing, eMBB data may or may not be successfully decoded at its receiver. This paper presents Cyrus+, a deep reinforcement learning (DRL)-based puncturing solution that employs goodput (through feedback from a receiver's decoder), rather than estimated raw throughput, in its design of reward function. Further, Cyrus+ is tailored specifically for the Open RAN (O-RAN) architecture and fully leverages O-RAN's three control loops at different time scales in its design of DRL. In the Non-Real-Time (Non-RT) RAN Intelligent Controller (RIC), Cyrus+ initializes the policy network that will be used in the RT Open Distributed Unit (O-DU). In the Near-RT RIC, Cyrus+ refines the policy based on dynamic network conditions and feedback from the receivers. In the RT O-DU, Cyrus+ generates a puncturing codebook by considering all possible URLLC arrivals. We build a standard-compliant link-level 5G NR simulator to demonstrate the efficacy of Cyrus+. Experimental results show that Cyrus+ outperforms benchmark puncturing algorithms and meets the stringent timing requirement in 5G NR (numerology 3). △ Less

Submitted 30 May, 2025; originally announced June 2025.

Comments: submitted to IEEE Transactions on Machine Learning in Communications and Networking. This is an extended version of the conference paper in https://ieeexplore.ieee.org/abstract/document/10637645. The manuscript is 17 pages long and includes 12 figures

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Authors: ByteDance Seed, :, Jiaze Chen, Tiantian Fan, Xin Liu, Lingjun Liu, Zhiqi Lin, Mingxuan Wang, Chengyi Wang, Xiangpeng Wei, Wenyuan Xu, Yufeng Yuan, Yu Yue, Lin Yan, Qiying Yu, Xiaochen Zuo, Chi Zhang, Ruofei Zhu, Zhecheng An, Zhihao Bai, Yu Bao, Xingyan Bin, Jiangjie Chen, Feng Chen, Hongmin Chen , et al. (249 additional authors not shown)

Abstract: We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 86.7 on AIME 2024, 55.0 on Codeforces and 77.3 on GPQA, demonstrating excellent reasoning abilities in STEM and coding. Beyond reasoning tasks, the method demonstrates notable generalization across diverse domains. For in… ▽ More We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 86.7 on AIME 2024, 55.0 on Codeforces and 77.3 on GPQA, demonstrating excellent reasoning abilities in STEM and coding. Beyond reasoning tasks, the method demonstrates notable generalization across diverse domains. For instance, it surpasses DeepSeek R1 by 8% in win rate on non-reasoning tasks, indicating its broader applicability. Compared to other state-of-the-art reasoning models, Seed1.5-Thinking is a Mixture-of-Experts (MoE) model with a relatively small size, featuring 20B activated and 200B total parameters. As part of our effort to assess generalized reasoning, we develop two internal benchmarks, BeyondAIME and Codeforces, both of which will be publicly released to support future research. Model trial link: https://www.volcengine.com/experience/ark. △ Less

Submitted 29 April, 2025; v1 submitted 10 April, 2025; originally announced April 2025.

StarCast: A Secure and Spectrum-Efficient Group Communication Scheme for LEO Satellite Networks

Authors: Chaoyu Zhang, Hexuan Yu, Shanghao Shi, Shaoyu Li, Yi Shi, Eric Burger, Y. Thomas Hou, Wenjing Lou

Abstract: Low Earth Orbit (LEO) satellite networks serve as a cornerstone infrastructure for providing ubiquitous connectivity in areas where terrestrial infrastructure is unavailable. With the emergence of Direct-to-Cell (DTC) satellites, these networks can provide direct access to mobile phones and IoT devices without relying on terrestrial base stations, leading to a surge in massive connectivity demands… ▽ More Low Earth Orbit (LEO) satellite networks serve as a cornerstone infrastructure for providing ubiquitous connectivity in areas where terrestrial infrastructure is unavailable. With the emergence of Direct-to-Cell (DTC) satellites, these networks can provide direct access to mobile phones and IoT devices without relying on terrestrial base stations, leading to a surge in massive connectivity demands for the serving satellite. To address this issue, group communication is an effective paradigm that enables simultaneous content delivery to multiple users and thus optimizes bandwidth reuse. Although extensive research has been conducted to improve group communication performance, securing this communication without compromising its inherent spectrum efficiency remains a critical challenge. To address this, we introduce StarCast, a secure group encryption scheme for LEO satellite networks. Our solution leverages ciphertext-policy attribute-based encryption (CP-ABE) to implement fine-grained access control by embedding access policies directly within the ciphertext. Unlike standard secure communication approaches that require dedicated per-user channels and significantly deplete limited satellite spectrum resources, StarCast maintains efficient spectrum reuse within user groups while ensuring that only authorized users can access transmitted data. Additionally, it significantly reduces the costly key management overhead associated with conventional encryption schemes. △ Less

Submitted 30 August, 2025; v1 submitted 11 February, 2025; originally announced February 2025.

UbiMoE: A Ubiquitous Mixture-of-Experts Vision Transformer Accelerator With Hybrid Computation Pattern on FPGA

Authors: Jiale Dong, Wenqi Lou, Zhendong Zheng, Yunji Qin, Lei Gong, Chao Wang, Xuehai Zhou

Abstract: Compared to traditional Vision Transformers (ViT), Mixture-of-Experts Vision Transformers (MoE-ViT) are introduced to scale model size without a proportional increase in computational complexity, making them a new research focus. Given the high performance and reconfigurability, FPGA-based accelerators for MoE-ViT emerge, delivering substantial gains over general-purpose processors. However, exist… ▽ More Compared to traditional Vision Transformers (ViT), Mixture-of-Experts Vision Transformers (MoE-ViT) are introduced to scale model size without a proportional increase in computational complexity, making them a new research focus. Given the high performance and reconfigurability, FPGA-based accelerators for MoE-ViT emerge, delivering substantial gains over general-purpose processors. However, existing accelerators often fall short of fully exploring the design space, leading to suboptimal trade-offs between resource utilization and performance. To overcome this problem, we introduce UbiMoE, a novel end-to-end FPGA accelerator tailored for MoE-ViT. Leveraging the unique computational and memory access patterns of MoE-ViTs, we develop a latency-optimized streaming attention kernel and a resource-efficient reusable linear kernel, effectively balancing performance and resource consumption. To further enhance design efficiency, we propose a two-stage heuristic search algorithm that optimally tunes hardware parameters for various FPGA resource constraints. Compared to state-of-the-art (SOTA) FPGA designs, UbiMoE achieves 1.34x and 3.35x throughput improvements for MoE-ViT on Xilinx ZCU102 and Alveo U280 platforms, respectively, while enhancing energy efficiency by 1.75x and 1.54x. Our implementation is available at https://github.com/DJ000011/UbiMoE. △ Less

Submitted 16 February, 2025; v1 submitted 8 February, 2025; originally announced February 2025.

Comments: Accepted by ISCAS 2025 (oral)

MedLeak: Multimodal Medical Data Leakage in Secure Federated Learning with Crafted Models

Authors: Shanghao Shi, Md Shahedul Haque, Abhijeet Parida, Chaoyu Zhang, Marius George Linguraru, Y. Thomas Hou, Syed Muhammad Anwar, Wenjing Lou

Abstract: Federated learning (FL) allows participants to collaboratively train machine learning models while keeping their data local, making it ideal for collaborations among healthcare institutions on sensitive data. However, in this paper, we propose a novel privacy attack called MedLeak, which allows a malicious FL server to recover high-quality site-specific private medical data from the client model u… ▽ More Federated learning (FL) allows participants to collaboratively train machine learning models while keeping their data local, making it ideal for collaborations among healthcare institutions on sensitive data. However, in this paper, we propose a novel privacy attack called MedLeak, which allows a malicious FL server to recover high-quality site-specific private medical data from the client model updates. MedLeak works by introducing an adversarially crafted model during the FL training process. Honest clients, unaware of the insidious changes in the published models, continue to send back their updates as per the standard FL protocol. Leveraging a novel analytical method, MedLeak can efficiently recover private client data from the aggregated parameter updates, eliminating costly optimization. In addition, the scheme relies solely on the aggregated updates, thus rendering secure aggregation protocols ineffective, as they depend on the randomization of intermediate results for security while leaving the final aggregated results unaltered. We implement MedLeak on medical image datasets (MedMNIST, COVIDx CXR-4, and Kaggle Brain Tumor MRI), as well as a medical text dataset (MedAbstract). The results demonstrate that our attack achieves high recovery rates and strong quantitative scores on both image and text datasets. We also thoroughly evaluate MedLeak across different attack parameters, providing insights into key factors that influence attack performance and potential defenses. Furthermore, we demonstrate that the recovered data can support downstream tasks such as disease classification with minimal performance loss. Our findings validate the need for enhanced privacy measures in FL systems, particularly for safeguarding sensitive medical data against powerful model inversion attacks. △ Less

Submitted 29 June, 2025; v1 submitted 13 July, 2024; originally announced July 2024.

Comments: Accepted by the IEEE/ACM conference on Connected Health: Applications, Systems and Engineering Technologies 2025 (CHASE'25)

BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning

Authors: Zhengyuan Jiang, Xingyu Lyu, Shanghao Shi, Yang Xiao, Yimin Chen, Y. Thomas Hou, Wenjing Lou, Ning Wanga

Abstract: Federated learning, while being a promising approach for collaborative model training, is susceptible to backdoor attacks due to its decentralized nature. Backdoor attacks have shown remarkable stealthiness, as they compromise model predictions only when inputs contain specific triggers. As a countermeasure, anomaly detection is widely used to filter out backdoor attacks in FL. However, the non-in… ▽ More Federated learning, while being a promising approach for collaborative model training, is susceptible to backdoor attacks due to its decentralized nature. Backdoor attacks have shown remarkable stealthiness, as they compromise model predictions only when inputs contain specific triggers. As a countermeasure, anomaly detection is widely used to filter out backdoor attacks in FL. However, the non-independent and identically distributed (non-IID) data distribution nature of FL clients presents substantial challenges in backdoor attack detection, as the data variety introduces variance among benign models, making them indistinguishable from malicious ones. In this work, we propose a novel distribution-aware backdoor detection mechanism, BoBa, to address this problem. To differentiate outliers arising from data variety versus backdoor attacks, we propose to break down the problem into two steps: clustering clients utilizing their data distribution, and followed by a voting-based detection. We propose a novel data distribution inference mechanism for accurate data distribution estimation. To improve detection robustness, we introduce an overlapping clustering method, where each client is associated with multiple clusters, ensuring that the trustworthiness of a model update is assessed collectively by multiple clusters rather than a single cluster. Through extensive evaluations, we demonstrate that BoBa can reduce the attack success rate to lower than 0.001 while maintaining high main task accuracy across various attack strategies and experimental settings. △ Less

Submitted 9 April, 2026; v1 submitted 12 July, 2024; originally announced July 2024.

Journal ref: ECAI 2025

Let the Noise Speak: Harnessing Noise for a Unified Defense Against Adversarial and Backdoor Attacks

Authors: Md Hasan Shahriar, Ning Wang, Naren Ramakrishnan, Y. Thomas Hou, Wenjing Lou

Abstract: The exponential adoption of machine learning (ML) is propelling the world into a future of distributed and intelligent automation and data-driven solutions. However, the proliferation of malicious data manipulation attacks against ML, namely adversarial and backdoor attacks, jeopardizes its reliability in safety-critical applications. The existing detection methods are attack-specific and built up… ▽ More The exponential adoption of machine learning (ML) is propelling the world into a future of distributed and intelligent automation and data-driven solutions. However, the proliferation of malicious data manipulation attacks against ML, namely adversarial and backdoor attacks, jeopardizes its reliability in safety-critical applications. The existing detection methods are attack-specific and built upon some strong assumptions, limiting them in diverse practical scenarios. Thus, motivated by the need for a more robust, unified, and attack-agnostic defense mechanism, we first investigate the shared traits of adversarial and backdoor attacks. Based on our observation, we propose NoiSec, a reconstruction-based intrusion detection system that brings a novel perspective by shifting focus from the reconstructed input to the reconstruction noise itself, which is the foundational root cause of such malicious data alterations. NoiSec disentangles the noise from the test input, extracts the underlying features from the noise, and leverages them to recognize systematic malicious manipulation. Our comprehensive evaluation of NoiSec demonstrates its high effectiveness across various datasets, including basic objects, natural scenes, traffic signs, medical images, spectrogram-based audio data, and wireless sensing against five state-of-the-art adversarial attacks and three backdoor attacks under challenging evaluation conditions. NoiSec demonstrates strong detection performance in both white-box and black-box adversarial attack scenarios, significantly outperforming the closest baseline models, particularly in an adaptive attack setting. We will provide the code for future baseline comparison. Our code and artifacts are publicly available at https://github.com/shahriar0651/NoiSec. △ Less

Submitted 13 April, 2025; v1 submitted 18 June, 2024; originally announced June 2024.

Comments: 20 pages, 9 figures

SoK: Public Blockchain Sharding

Authors: Md Mohaimin Al Barat, Shaoyu Li, Changlai Du, Y. Thomas Hou, Wenjing Lou

Abstract: Blockchain's decentralization, transparency, and tamper-resistance properties have facilitated the system's use in various application fields. However, the low throughput and high confirmation latency hinder the widespread adoption of Blockchain. Many solutions have been proposed to address these issues, including first-layer solutions (or on-chain solutions) and second-layer solutions (or off-cha… ▽ More Blockchain's decentralization, transparency, and tamper-resistance properties have facilitated the system's use in various application fields. However, the low throughput and high confirmation latency hinder the widespread adoption of Blockchain. Many solutions have been proposed to address these issues, including first-layer solutions (or on-chain solutions) and second-layer solutions (or off-chain solutions). Among the proposed solutions, the blockchain sharding system is the most scalable one, where the nodes in the network are divided into several groups. The nodes in different shards work in parallel to validate the transactions and add them to the blocks, and in such a way, the throughput increases significantly. However, previous works have not adequately summarized the latest achievements in blockchain sharding, nor have they fully showcased its state-of-the-art. Our study provides a systemization of knowledge of public blockchain sharding, including the core components of sharding systems, challenges, limitations, and mechanisms of the latest sharding protocols. We also compare their performance and discuss current constraints and future research directions. △ Less

Submitted 30 May, 2024; originally announced May 2024.

Comments: 18 pages

ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models

Authors: Heng Jin, Chaoyu Zhang, Shanghao Shi, Wenjing Lou, Y. Thomas Hou

Abstract: Large language models (LLMs) have attracted significant attention in recent years. Due to their "Large" nature, training LLMs from scratch consumes immense computational resources. Since several major players in the artificial intelligence (AI) field have open-sourced their original LLMs, an increasing number of individuals and smaller companies are able to build derivative LLMs based on these ope… ▽ More Large language models (LLMs) have attracted significant attention in recent years. Due to their "Large" nature, training LLMs from scratch consumes immense computational resources. Since several major players in the artificial intelligence (AI) field have open-sourced their original LLMs, an increasing number of individuals and smaller companies are able to build derivative LLMs based on these open-sourced models at much lower costs. However, this practice opens up possibilities for unauthorized use or reproduction that may not comply with licensing agreements, and fine-tuning can change the model's behavior, thus complicating the determination of model ownership. Current intellectual property (IP) protection schemes for LLMs are either designed for white-box settings or require additional modifications to the original model, which restricts their use in real-world settings. In this paper, we propose ProFLingo, a black-box fingerprinting-based IP protection scheme for LLMs. ProFLingo generates queries that elicit specific responses from an original model, thereby establishing unique fingerprints. Our scheme assesses the effectiveness of these queries on a suspect model to determine whether it has been derived from the original model. ProFLingo offers a non-invasive approach, which neither requires knowledge of the suspect model nor modifications to the base model or its training process. To the best of our knowledge, our method represents the first black-box fingerprinting technique for IP protection for LLMs. Our source code and generated queries are available at: https://github.com/hengvt/ProFLingo. △ Less

Submitted 10 September, 2024; v1 submitted 3 May, 2024; originally announced May 2024.

Comments: This is the author's pre-print version of the work. It is posted here for your personal use. Not for redistribution

Cell Graph Transformer for Nuclei Classification

Authors: Wei Lou, Guanbin Li, Xiang Wan, Haofeng Li

Abstract: Nuclei classification is a critical step in computer-aided diagnosis with histopathology images. In the past, various methods have employed graph neural networks (GNN) to analyze cell graphs that model inter-cell relationships by considering nuclei as vertices. However, they are limited by the GNN mechanism that only passes messages among local nodes via fixed edges. To address the issue, we devel… ▽ More Nuclei classification is a critical step in computer-aided diagnosis with histopathology images. In the past, various methods have employed graph neural networks (GNN) to analyze cell graphs that model inter-cell relationships by considering nuclei as vertices. However, they are limited by the GNN mechanism that only passes messages among local nodes via fixed edges. To address the issue, we develop a cell graph transformer (CGT) that treats nodes and edges as input tokens to enable learnable adjacency and information exchange among all nodes. Nevertheless, training the transformer with a cell graph presents another challenge. Poorly initialized features can lead to noisy self-attention scores and inferior convergence, particularly when processing the cell graphs with numerous connections. Thus, we further propose a novel topology-aware pretraining method that leverages a graph convolutional network (GCN) to learn a feature extractor. The pre-trained features may suppress unreasonable correlations and hence ease the finetuning of CGT. Experimental results suggest that the proposed cell graph transformer with topology-aware pretraining significantly improves the nuclei classification results, and achieves the state-of-the-art performance. Code and models are available at https://github.com/lhaof/CGT △ Less

Submitted 20 February, 2024; originally announced February 2024.

Comments: AAAI 2024, Code and models are available at https://github.com/lhaof/CGT

Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction

Authors: Shanghao Shi, Ning Wang, Yang Xiao, Chaoyu Zhang, Yi Shi, Y. Thomas Hou, Wenjing Lou

Abstract: Federated learning is known for its capability to safeguard the participants' data privacy. However, recently emerged model inversion attacks (MIAs) have shown that a malicious parameter server can reconstruct individual users' local data samples from model updates. The state-of-the-art attacks either rely on computation-intensive iterative optimization methods to reconstruct each input batch, mak… ▽ More Federated learning is known for its capability to safeguard the participants' data privacy. However, recently emerged model inversion attacks (MIAs) have shown that a malicious parameter server can reconstruct individual users' local data samples from model updates. The state-of-the-art attacks either rely on computation-intensive iterative optimization methods to reconstruct each input batch, making scaling difficult, or involve the malicious parameter server adding extra modules before the global model architecture, rendering the attacks too conspicuous and easily detectable. To overcome these limitations, we propose Scale-MIA, a novel MIA capable of efficiently and accurately reconstructing local training samples from the aggregated model updates, even when the system is protected by a robust secure aggregation (SA) protocol. Scale-MIA utilizes the inner architecture of models and identifies the latent space as the critical layer for breaching privacy. Scale-MIA decomposes the complex reconstruction task into an innovative two-step process. The first step is to reconstruct the latent space representations (LSRs) from the aggregated model updates using a closed-form inversion mechanism, leveraging specially crafted linear layers. Then in the second step, the LSRs are fed into a fine-tuned generative decoder to reconstruct the whole input batch. We implemented Scale-MIA on commonly used machine learning models and conducted comprehensive experiments across various settings. The results demonstrate that Scale-MIA achieves excellent performance on different datasets, exhibiting high reconstruction rates, accuracy, and attack efficiency on a larger scale compared to state-of-the-art MIAs. Our code is available at https://github.com/unknown123489/Scale-MIA. △ Less

Submitted 27 November, 2024; v1 submitted 9 November, 2023; originally announced November 2023.

Comments: Accepted by Network and Distributed System Security (NDSS) Symposium 2025