Showing 1–50 of 1,094 results for author: Song, S

$\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution

Authors: Aofan Liu, Shiyuan Song, Yiyan Qi

Abstract: LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize each task in isolation, discarding search experience after completion. We introduce $\varepsilon$-MemEvo, a framework for cross-task knowledge transfer in LLM program evolution. $\varepsilon$-MemEvo stores prior experience as task-agnostic tactic memo… ▽ More LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize each task in isolation, discarding search experience after completion. We introduce $\varepsilon$-MemEvo, a framework for cross-task knowledge transfer in LLM program evolution. $\varepsilon$-MemEvo stores prior experience as task-agnostic tactic memories: compact natural-language summaries of successful algorithmic strategies rather than raw code, enabling transfer across tasks with different APIs and evaluators. To avoid negative transfer from semantically mismatched memories, $\varepsilon$-MemEvo uses an adaptive injection gate that decides whether retrieved memories should be injected, and at what intensity. We evaluate $\varepsilon$-MemEvo on 8 diverse optimization benchmarks spanning mathematical optimization and systems engineering, using a content-level Leave-One-Out protocol that excludes target-task memory entries. On the primary GPT-5 backbone, $\varepsilon$-MemEvo improves AUCC over AdaEvolve on all 8 tasks, with a mean relative gain of +8.7%, and improves early-stage convergence by +9.4% on average. Ablations show that naive memory injection can fail catastrophically, while adaptive gating remains safe across all five ablation tasks. The data-updated posterior is interpretable in observed states: it favors skip during improving search and shifts from skip to hint across early and late plateaus. These gains incur less than 1% computational overhead. △ Less

Submitted 12 August, 2026; originally announced August 2026.

ACM Class: I.2.6; I.2.8

ImpactHO: Importance-Aware KV Cache Transfer for Multi-User Edge LLM Handover

Authors: Minwoo Kim, Soochang Song, Namyoon Lee, Bang Chul Jung, Yongjune Kim

Abstract: Edge LLMs must preserve inference continuity when a user hands over between edge nodes, requiring key-value (KV) cache transfer to the target node. However, simultaneous handovers saturate the backhaul, preventing full cache delivery within the mobility-imposed transfer window. Rather than allocating bandwidth as if all cache entries were equally valuable, we order each user's KV cache by importan… ▽ More Edge LLMs must preserve inference continuity when a user hands over between edge nodes, requiring key-value (KV) cache transfer to the target node. However, simultaneous handovers saturate the backhaul, preventing full cache delivery within the mobility-imposed transfer window. Rather than allocating bandwidth as if all cache entries were equally valuable, we order each user's KV cache by importance and transmit only its most informative fraction, turning token-level sparsity into communication savings. We cast the transfer as a multi-user backhaul allocation problem that maximizes average accuracy across users. Each user's partial-cache accuracy serves as its utility: a sigmoid that fits measurements on the RULER benchmark with $R^2>0.99$ across models and context lengths. Because importance ordering front-loads the high-value entries, the concave region of the accuracy curve spans nearly the entire cache. Our proposed allocator keeps served users within this region, making each per-slot allocation problem convex. The optimum is derived via a closed-form weighted water-filling solution that generalizes information-theoretic water-filling and enables online scheduling. The proposed allocator attains over 93.7% average accuracy in a 500ms transfer window, within 0.5pp of the full-cache ceiling, and reaches 98.2-99.5% of a clairvoyant upper bound. △ Less

Submitted 11 August, 2026; originally announced August 2026.

An Asynchronous Triggered MAC Protocol for Underwater Acoustic Networks

Authors: Bingwen Huangfu, Jiani Guo, Shanshan Song, Nan Sun, Jun Liu, Miao Pan

Abstract: Time Division Multiple Access (TDMA)-based Medium Access Control (MAC) protocols have proven their practicality through extensive field trials in Underwater Acoustic Networks (UANs), attributable to their hardware compatibility and ease of implementation. In conventional TDMA-based MAC designs, channel access is typically organized using synchronized, fixed-length slots to mitigate contention and… ▽ More Time Division Multiple Access (TDMA)-based Medium Access Control (MAC) protocols have proven their practicality through extensive field trials in Underwater Acoustic Networks (UANs), attributable to their hardware compatibility and ease of implementation. In conventional TDMA-based MAC designs, channel access is typically organized using synchronized, fixed-length slots to mitigate contention and coordinate transmissions. However, this paradigm imposes significant clock synchronization overhead in UANs with long and variable propagation delays and struggles to improve scheduling flexibility. Although some protocols attempt to refine this slot paradigm (adjust the slot length to improve channel reuse efficiency or scheduling frequency), they are still constrained by the trade-off between channel utilization and scheduling complexity. To this end, this paper proposes AT-MAC, an Asynchronous Triggered MAC protocol that aims to achieve efficient and fair channel access through coordinated asynchronous scheduling. AT-MAC introduces a triggered slot paradigm without time synchronization, decoupling transmission scheduling from a rigid timeline and enabling asynchronous, variable-length slots to accommodate the long and diverse propagation delays. To power this slot paradigm, AT-MAC augments conventional Multi-Agent Deep Reinforcement Learning to handle asynchronous interaction, achieving coordinated channel access under partial observations. It further devises a load-aware fairness guard mechanism to enable network-wide fairness status inference solely through local overhearing, thereby guiding adaptive scheduling correction to maintain fairness. Field-reconstructed simulations and on-board inference benchmarking demonstrate the feasibility of AT-MAC. Extensive simulation results further demonstrate its consistent performance gains across the evaluated scenarios and traffic conditions. △ Less

Submitted 15 August, 2026; v1 submitted 11 August, 2026; originally announced August 2026.

LAD-COD: Language-Aligned Dense Perception for Camouflaged Object Detection

Authors: Shangye Song, Tianzhi Zhu, Syed Ariff Syed Hesham, Xin He, Yun Liu

Abstract: Camouflaged object detection (COD) aims to segment objects that exhibit high visual similarity to their surroundings, which reduces foreground-background discriminability and weakens boundary evidence across appearance, texture, and structure. Such limitations motivate the use of instruction-conditioned semantics as top-down guidance for identifying which weak visual cues are relevant to the targe… ▽ More Camouflaged object detection (COD) aims to segment objects that exhibit high visual similarity to their surroundings, which reduces foreground-background discriminability and weakens boundary evidence across appearance, texture, and structure. Such limitations motivate the use of instruction-conditioned semantics as top-down guidance for identifying which weak visual cues are relevant to the target. Recent segmentation systems built on large multimodal models (LMMs) demonstrate this possibility through instruction-conditioned target embeddings that guide mask decoding. However, in this language-to-mask paradigm, the generated target embedding conditions mainly the mask decoder, leaving the dense visual features that must preserve low-contrast boundaries and fine local structure without explicit guidance. We propose Language-Aligned Dense perception for COD (LAD-COD), a framework that aligns top-down semantic target guidance with bottom-up hierarchical visual features. Instead of fully adapting a large generic image encoder, LAD-COD learns a trainable hierarchical visual branch that captures camouflage-sensitive texture, boundary, and contextual information. To align these features with the target embedding, LAD-COD applies Language-Aligned Dual Visual Fusion (LADVF), which extends the embedding beyond sparse prompting to query patch-level language-aligned features and to gate their residual integration with the hierarchical features. This design allows semantic information to guide localization while preserving the fine structural details needed for camouflage segmentation. Experiments on CAMO, COD10K, and NC4K show that LAD-COD obtains the best reported value in all 12 dataset-metric comparisons. △ Less

Submitted 8 August, 2026; originally announced August 2026.

GSBF: Gaussian Splatting for Environment-Aware Beamforming

Authors: Yijie Bian, Wei Guo, Zixin Wang, Shenghui Song, Jun Zhang, Khaled B. Letaief

Abstract: Beamforming plays a key role in multiple-input-multiple-output (MIMO) communication systems. However, conventional beamforming design normally requires accurate instantaneous channel state information (CSI) and iterative optimization, which incur substantial pilot overhead and computational complexity. Recognizing that radio propagation is intrinsically governed by the physical geometry, we develo… ▽ More Beamforming plays a key role in multiple-input-multiple-output (MIMO) communication systems. However, conventional beamforming design normally requires accurate instantaneous channel state information (CSI) and iterative optimization, which incur substantial pilot overhead and computational complexity. Recognizing that radio propagation is intrinsically governed by the physical geometry, we develop a 3D Gaussian splatting for environment-aware beamforming (GSBF) pipeline based on multi-modal data, which characterizes the environment through a persistent 3D Gaussian representation. Specifically, GSBF models the environmental scattering response with reciprocity-preserving bidirectional spherical Gaussian (Bi-SG) kernels and performs two-sided electromagnetic rasterization to render an angular propagator map. The rendered map is then aggregated through an over-complete array-manifold dictionary and projected to the constant-modulus beamformers, thereby synthesizing beams directly from the access point (AP) pose and user position without online instantaneous CSI. Simulations demonstrate that GSBF consistently outperforms baselines such as exhaustive beam alignment (EBA) with lower latency. △ Less

Submitted 15 August, 2026; v1 submitted 6 August, 2026; originally announced August 2026.

ACA-GS: Adaptive-Capacity Anchored Gaussian Splatting for Compact Dynamic Radiance Fields

Authors: Seunghyeon Song, Joo Chan Lee, Chanung Park, Jun Young Jeong, Minseo Lee, Eunbyung Park, Jong Hwan Ko

Abstract: Recent advances in 4D Gaussian Splatting (4DGS) enable high-fidelity, real-time spatiotemporal rendering, but expose a fundamental trade-off between motion expressiveness and storage efficiency. While anchor-based designs achieve compactness through anchor-level parameter sharing, their rigid uniform parametrization enforces fixed Neural Gaussian counts and feature budgets per anchor. Consequently… ▽ More Recent advances in 4D Gaussian Splatting (4DGS) enable high-fidelity, real-time spatiotemporal rendering, but expose a fundamental trade-off between motion expressiveness and storage efficiency. While anchor-based designs achieve compactness through anchor-level parameter sharing, their rigid uniform parametrization enforces fixed Neural Gaussian counts and feature budgets per anchor. Consequently, insufficient fidelity is addressed by excessive anchor density, rather than lightweight, targeted increases in Neural Gaussian count or feature capacity, resulting in memory waste. To overcome this rigidity, we introduce an adaptive-capacity anchor-based framework that dynamically allocates the representational capacity based on local spatiotemporal demands. Adaptive Anchor Cardinality varies the number of Neural Gaussians per anchor, concentrating primitives in regions of high geometric or motion complexity while suppressing redundancy. In parallel, Adaptive Anchor Feature Masking modulates anchor-level feature channels, assigning rich features to complex regions and lightweight representations to simpler ones. Experiments on MPEG, Panoptic Sports, and N3DV datasets demonstrate substantial storage reduction without degrading visual quality. Notably, on challenging MPEG sequences with complex motion, our method achieves up to 1.5x higher compression than state-of-the-art anchor-based methods while preserving comparable quality. △ Less

Submitted 5 August, 2026; originally announced August 2026.

Comments: 9 pages, 8 figures. Accepted to ACM Multimedia 2026

Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate

Authors: Hao Wu, Shoucheng Song, Chang Yao, Haoyu Wang, Huaiyu Wan, Youfang Lin, Kai Lv

Abstract: Multi-Agent Debate (MAD) improves the reasoning performance of Large Language Models (LLMs) through multi-round interaction. However, LLMs in MAD are highly susceptible to blind conformity. Existing individual evaluation methods, typically based on confidence or perplexity, fail to reflect the correctness of reasoning and may even exacerbate blind conformity. To address this, we shift the perspect… ▽ More Multi-Agent Debate (MAD) improves the reasoning performance of Large Language Models (LLMs) through multi-round interaction. However, LLMs in MAD are highly susceptible to blind conformity. Existing individual evaluation methods, typically based on confidence or perplexity, fail to reflect the correctness of reasoning and may even exacerbate blind conformity. To address this, we shift the perspective from individual evaluation to group interaction. We define mutual referencing among LLMs as \textbf{Debate Relationships} and recognize that regulating these relationships is the key to mitigating blind conformity. In this paper, we propose a novel framework for \textbf{D}ynamically r\textbf{E}gulating deb\textbf{A}te \textbf{R}elationships (DEAR) from the group perspective. At first, DEAR quantifies consensus and divergence as \textit{group evidence} to capture the debate state. Then, DEAR operates through three stages: 1) What: perceiving group consultation tendency and uncertainty; 2) Who: introducing a Selection RL-Agent to dynamically select reference peers; and 3) How: adopting a Behavior RL-Agent to adaptively adjust generation behaviors. Notably, we formulate the execution of the two RL-Agents as a sequential decision-making process, jointly optimizing via multi-agent reinforcement learning. Extensive experiments demonstrate that DEAR achieves superior performance while significantly reducing token consumption. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Riemannian Attention Mechanisms for Transformers: A Theoretical Framework and Architecture Design

Authors: Sen Song

Abstract: All Transformer-based large language models compute attention via the Euclidean inner product, an architectural choice that Dong et al. (2021) proved causes representational rank to decay doubly exponentially with depth in pure self-attention stacks. We develop a theoretical framework that targets this structural limitation at the mathematical level by replacing the flat Euclidean metric with lear… ▽ More All Transformer-based large language models compute attention via the Euclidean inner product, an architectural choice that Dong et al. (2021) proved causes representational rank to decay doubly exponentially with depth in pure self-attention stacks. We develop a theoretical framework that targets this structural limitation at the mathematical level by replacing the flat Euclidean metric with learned per-token Riemannian metrics. Our contributions are threefold. (1) We prove that Riemannian attention scores with heterogeneous per-token metrics are non-Gram---they cannot be factorized as QK^T with factorization dimension O(d). We are explicit that this is a structural observation, not a proof of rank preservation. (2) We establish that low-rank metric factors render all geometric operations tractable: geodesic distance in O(d*r) per token and metric inversion in O(d*r^2) via the Woodbury identity---both far below the O(d^3) cost of a general matrix---making Riemannian attention feasible at billion-parameter scale with negligible overhead. (3) We present the Fiber Bundle Transformer, a complete architecture specification in which each token position carries its own Riemannian metric, attention is geodesic distance computation, feed-forward updates use metric-preconditioned steps, and the connection carries explicit curvature and torsion proxies. We derive formal predictions about correctly implemented geometric architectures and identify the central open problem: proving or disproving that heterogeneous Riemannian metrics prevent the rank collapse that row-stochastic attention matrices otherwise cause. This paper presents theoretical analysis and architectural design; empirical validation is the subject of future work. △ Less

Submitted 2 August, 2026; originally announced August 2026.

Comments: 23 pages, theoretical paper

MSC Class: 68T50; 68T07; 53B20 ACM Class: I.2.7; I.2.6; F.2.2

EEG-JEPA: Structured Latent Prediction for EEG Foundation Models

Authors: Jinhao Li, Zhiyuan Ma, Xueqiao Han, Zhongye Xia, Xinche Zhang, Shanghong Xie, Yixuan Liu, Yongjian Li, Runmin Gan, Tianlin Huo, Sen Song

Abstract: Electroencephalography (EEG) foundation models aim to learn reusable representations from large-scale unlabeled recordings. A common pretraining strategy is masked waveform reconstruction, but applying supervision directly to noisy EEG may encourage models to recover predictable background activity, acquisition effects, and artifacts rather than neural structure that transfers across tasks. This r… ▽ More Electroencephalography (EEG) foundation models aim to learn reusable representations from large-scale unlabeled recordings. A common pretraining strategy is masked waveform reconstruction, but applying supervision directly to noisy EEG may encourage models to recover predictable background activity, acquisition effects, and artifacts rather than neural structure that transfers across tasks. This raises a central question: what should an EEG foundation model predict to learn transferable representations? We introduce EEG-JEPA a structured latent-prediction framework for EEG foundation modeling. Rather than reconstructing masked voltage samples, a masked context encoder and predictor infer contextual latent states produced by an exponential-moving-average target encoder that observes the complete input. EEG-JEPA organizes target design along three complementary dimensions: target content specifies what representation is predicted, target support specifies where prediction occurs over structured electrode--time regions through Neurotopology-Aware Multi-scale Electrode-Temporal Masking (N-MET), and target depth specifies at which encoder layers supervision is applied. Together, these designs shift EEG pretraining from recovering missing measurements to inferring latent states from structured electrode--time context. We evaluate EEG-JEPA through controlled objective comparisons, frozen multitask transfer, and full fine-tuning. Under the same backbone, pretraining corpus, and training duration, EEG-JEPA improves the 14-task frozen macro balanced accuracy from 40.49% to 50.42% over CBraMod-style masked waveform reconstruction. Multi-source continuation further raises this result to 52.94%, the highest average among the EEG foundation models evaluated on EEG-FM-Bench. Under protocol-matched full fine-tuning, EEG-JEPA also improves the nine-task average balanced accuracy from 68.98% to 70.65%. △ Less

Submitted 31 July, 2026; originally announced August 2026.

Comments: 9 pages, 6 figures

MSCM-net: A hyperspectral image classiffcation method based on multi-scale convolution and Mamba

Authors: Jianjun Chen, Linlin Wang, Lifang Chang, Limin Huo, Shujiang Song, Yanjia Zhao, Mingwei Shao

Abstract: Hyperspectral imaging is widely used in remote sensing and engineering. Therefore, research on its classification methods is crucial. While CNN and Transformer-based methods have advanced, they still face locality constraints and high computational complexity. To address these issues, we propose an innovative hyperspectral image classification model, MSCM-net. Specifically, first of all, a model a… ▽ More Hyperspectral imaging is widely used in remote sensing and engineering. Therefore, research on its classification methods is crucial. While CNN and Transformer-based methods have advanced, they still face locality constraints and high computational complexity. To address these issues, we propose an innovative hyperspectral image classification model, MSCM-net. Specifically, first of all, a model architecture combining multi-scale CNN and Mamba is proposed. It consists of a multi-scale feature extraction module (MCSE) and multiple stacked Mamba blocks, which integrates the local feature extraction capability of multi-scale CNN and the long sequence modeling advantage of Mamba. Secondly, the proposed MCSE module consists of multi-scale convolution and SENet. Convolution kernels of different scales extract local information with different receptive fields, enhancing the fusion of spatial and spectral information. Meanwhile, the SENet enables the model to automatically learn the importance of each channel in the multi-scale features. Furthermore, we also propose a dual-branch feature aggregation module, which further effectively extracts and integrates the spectral information contained in the central pixel and the spatial information in the surrounding pixels. Our model has undergone numerous experiments on three widely used benchmark datasets. The experimental results show that MSCM-net can achieve advanced classification performance while reducing computational complexity. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Rethinking EEG-Based Disease Diagnosis: Decoupling Instance Representation Learning from Subject-Level Supervision

Authors: Zhiyuan Ma, Zeyuan Li, Zhiyi Lu, Jiacheng Hao, Youlang Du, Zhen Jiang, Xinche Zhang, Yuhao Sun, Xinke Shen, Sen Song

Abstract: EEG-based disease diagnosis requires one prediction per subject, yet common pipelines segment recordings into short instances, inherit the subject label for every instance, and train instance-level classifiers. This assumes that all instances provide equally reliable diagnostic evidence. Multiple instance learning (MIL) avoids inherited labels by treating each subject as a bag. However, EEG datase… ▽ More EEG-based disease diagnosis requires one prediction per subject, yet common pipelines segment recordings into short instances, inherit the subject label for every instance, and train instance-level classifiers. This assumes that all instances provide equally reliable diagnostic evidence. Multiple instance learning (MIL) avoids inherited labels by treating each subject as a bag. However, EEG datasets contain far fewer subjects than instances, which can limit the quality of the representations learned by end-to-end MIL. We propose BridgeMIL, a two-stage framework that decouples instance representation learning from subject-level supervision. Stage 1 pretrains the encoder without inherited instance labels by aligning temporally nearby windows and independently sampled within-subject sub-bags. Variance and covariance regularization prevent collapse and reduce redundancy without negative pairs. Stage 2 transfers the encoder to an attention-based MIL aggregator, applies supervision only to subject predictions, and limits representation drift through feature retention. Across three EEG disease datasets and five representative backbones, BridgeMIL attains the highest mean accuracy in 14 of 15 dataset-backbone settings and an overall mean accuracy of 76.57%, 4.28 percentage points higher than the strongest baseline. Further analyses reveal substantial variation in inherited-label reliability across instances, greater performance sensitivity to subject scarcity than to instance scarcity, and a more structured representation space with distinct subject-wise clusters and improved separation between diagnostic classes. Together, these findings underscore the importance of aligning supervision with the subject-level prediction objective while learning from abundant EEG instances without assigning disease labels to individual instances. △ Less

Submitted 31 July, 2026; v1 submitted 29 July, 2026; originally announced July 2026.

Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design

Authors: Huy Ha, C. Karen Liu, Shuran Song

Abstract: An often overlooked factor of robot manipulation performance is the embodiment of the robot itself. Motivated by this problem, we study motion-conditioned robot co-design, where the goal is to generate complete robot designs that track target end-effector trajectories (from human demonstrations) while optimizing user-defined rewards. We introduce Transformer Transformer, a diffusion transformer tr… ▽ More An often overlooked factor of robot manipulation performance is the embodiment of the robot itself. Motivated by this problem, we study motion-conditioned robot co-design, where the goal is to generate complete robot designs that track target end-effector trajectories (from human demonstrations) while optimizing user-defined rewards. We introduce Transformer Transformer, a diffusion transformer trained on RoboTokens, a unified tokenization of robot embodiments, states, and actions. The same architecture can be used across embodiment spaces (e.g., wheeled bimanual, quadrupeds, humanoids) and use cases (embodiment generation, cross embodiment controller). Rather than overfitting to one reward function, Transformer Transformer is a dynamics model, whose reward-agnostic state and action predictions can be converted into reward-specific value predictions. These value predictions are used to steer embodiment diffusion towards high value robot designs, through a procedure we call Dynamics Self-Guidance. Experiments across multiple design spaces show zero-shot optimization of unseen rewards and trajectories, improving performance and runtime over the evolutionary baseline. Finally, we fabricated an optimized ALOHA design, which reduced tracking error by over 70% compared to the original design. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Comments: 26 pages, 12 figures, 20 tables. Project page: https://transformer-transformer.github.io

ACM Class: I.2.9; I.2.6

Reasoning or Memorization: Can LLMs Understand and Generate Chinese Xiehouyu Riddles?

Authors: Hai Hu, Siyuan Song, Chongtian Shao, Kejia Zhang, Tianjian Zhu, Xiaojing Zhao

Abstract: In this paper, we push the boundary of LLM reasoning by testing them in a Chinese language game, xiehouyu, with novel xiehouyu created by linguists that had not existed before to avoid data contamination. We use multiple-choice questions (MCQ), free-form explanation generation, and new xiehouyu creation to evaluate LLMs' ability to understand and create xiehouyu. In MCQ, we use the delta of accura… ▽ More In this paper, we push the boundary of LLM reasoning by testing them in a Chinese language game, xiehouyu, with novel xiehouyu created by linguists that had not existed before to avoid data contamination. We use multiple-choice questions (MCQ), free-form explanation generation, and new xiehouyu creation to evaluate LLMs' ability to understand and create xiehouyu. In MCQ, we use the delta of accuracy ($Δ_{acc}$) between existing but low-frequency xiehouyu and novel ones as an index for memorization. $Δ_{acc}$ for native speakers is very low, suggesting similar processing mechanisms. However, we found that frontier Chinese models have on average a $Δ_{acc}$ of 23.6\%, while English-centric models tested have a mean $Δ_{acc}$ of 5.1\%, suggesting that frontier Chinese models are likely trained with much larger Chinese data, thus memorizing more low-frequency xiehouyu. For novel xiehouyu, Gemini 3.1 Pro demonstrated remarkable ability with acc 92.6, which is 24\% higher than human accuracy. In xiehouyu creation, those created by LLMs receive much worse ratings than those by humans. These results suggest that claims about the reasoning abilities of LLMs may need careful re-examination considering the data contamination issue, and that LLMs' creativity in language-related tasks may still be behind human experts, at least in Chinese xiehouyu. △ Less

Submitted 25 July, 2026; originally announced July 2026.

Comments: 20 pages; exp 3 is work in progress

From Signals to Behaviors: Evidence-Based Android Malware Detection

Authors: Shiwen Song, Yiheng Xiong, Sen Chen, Xiaofei Xie

Abstract: Android malware remains a persistent threat, and detecting it accurately is a long-standing open problem. Whether an app is malicious depends on what it actually does and the context in which it does it, not on the surface signals it happens to exhibit. Existing detectors instead reason about proxies for behavior, such as learned features or local code slices, and flag whatever deviates from these… ▽ More Android malware remains a persistent threat, and detecting it accurately is a long-standing open problem. Whether an app is malicious depends on what it actually does and the context in which it does it, not on the surface signals it happens to exhibit. Existing detectors instead reason about proxies for behavior, such as learned features or local code slices, and flag whatever deviates from these proxies as malicious. But deviation is not maliciousness: benign apps that merely look unusual are over-flagged, evolving malware that looks ordinary slips through. We argue that detection should be behavior-oriented: recover an app's potentially malicious behaviors and judge which are truly malicious. To realize this, we present Praxis, which structures detection as a hypothesize-confirm-judge pipeline: it hypothesizes candidate behaviors from coarse static signals, confirms each by grounding it in code evidence verified with program analysis, and judges the confirmed behaviors in context: the user's awareness, the app's functional context, and how they compose into an attack. For a malicious app, Praxis returns a verdict and the supported behaviors. We evaluate Praxis against seven baselines across three challenging settings. It achieves the best overall detection performance (87.4% F1), outperforming the baselines by 18.6-34.8 percentage points. On high-permission benign apps, it reduces the false-positive rate to 13.0%, a reduction of 41.1-67.0 percentage points compared with the baselines. Beyond binary detection, Praxis recovers fine-grained malicious behaviors at 87.3% F1, outperforming prior behavior-level approaches by 56.5-73.4 percentage points. Ablation studies show that each stage of the pipeline contributes to the final performance. △ Less

Submitted 25 July, 2026; originally announced July 2026.

Comments: 12 pages, 6 figures

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning

Authors: Xiaokun Wang, Siyu Song, Wentao Liu, Xiaodong Zou

Abstract: Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes. We present HeuristicEdu, a two-phase pipeline that aligns Qwen2.5-7B toward Socratic tutoring via supervised warm-up and Group Relative Policy Optimization (GRPO).… ▽ More Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes. We present HeuristicEdu, a two-phase pipeline that aligns Qwen2.5-7B toward Socratic tutoring via supervised warm-up and Group Relative Policy Optimization (GRPO). Training uses SocraticEdu, 797 multi-turn Chinese children's science dialogues reconstructed from a live platform, with a heuristic reward over cognitive depth (R_cog), curiosity engagement (R_eng), and directness (R_dir), together with a K_query correction for student-introduced terms. We introduce Scaffolding Effectiveness (SE) and Conversation Depth (CD) to evaluate outcomes beyond surface fluency. On 30 held-out questions, the best GRPO variant improves SE from 30.0% to 63.3% and lowers keyword leakage from 30.0% to 13.3%. Notably, this best variant omits the directness penalty during optimization, suggesting that explicit anti-leakage terms can conflict with gradient-based behavioral alignment. An unaligned Qwen-72B baseline reaches 0% SE and 96.7% leakage, showing that scale alone does not induce Socratic behavior. △ Less

Submitted 24 July, 2026; originally announced July 2026.

Comments: 12 pages, 2 figures, 5 tables; includes an appendix

ModPack: An Extensible Teleoperation Interface for Bimanual Mobile Manipulation

Authors: Joshua Citron, Renee Zbizika, Zeyi Liu, Shuran Song

Abstract: Existing teleoperation systems are often tailored to specific robot hardware and task domains, limiting their scalability and adaptability. We present ModPack, a modular and extensible teleoperation system designed to support diverse robot embodiments and task requirements within a unified framework. At the core of ModPack is a self-contained wearable "backpack" that integrates onboard computation… ▽ More Existing teleoperation systems are often tailored to specific robot hardware and task domains, limiting their scalability and adaptability. We present ModPack, a modular and extensible teleoperation system designed to support diverse robot embodiments and task requirements within a unified framework. At the core of ModPack is a self-contained wearable "backpack" that integrates onboard computation, power, communication, and data storage. Built on top of this shared interface, the system supports plug-and-play capability modules including joint-level teleoperation with haptic feedback, mobile manipulation, and active perception. Experiments across two distinct robot platforms and real-world mobile manipulation tasks demonstrate that ModPack provides a flexible and reusable framework for data collection and policy learning. To support future research, we open-source the complete hardware design and software stack. Project website: https://modpack-robotics.github.io/ △ Less

Submitted 21 July, 2026; originally announced July 2026.

Dual Attention Residuals

Authors: Xingda Yu, Yining Li, Xinzhang Liu, Zhihao Yang, Haowei He, Chao Wang, Yongxiang Li, Shuangyong Song

Abstract: Recent work extends Transformer residual pathways along two complementary axes: historical retrieval selects information from earlier depths, whereas multi-stream methods maintain multiple residual trajectories. These capabilities have largely been studied in isolation, and assigning an independent retriever to each stream still prevents one trajectory from influencing depth selection in another.… ▽ More Recent work extends Transformer residual pathways along two complementary axes: historical retrieval selects information from earlier depths, whereas multi-stream methods maintain multiple residual trajectories. These capabilities have largely been studied in isolation, and assigning an independent retriever to each stream still prevents one trajectory from influencing depth selection in another. We propose Dual Attention Residuals (DAR), which brings multi-stream interaction into historical retrieval through reciprocal cross-stream addressing. For each target stream, DAR computes depth weights from normalized states in the opposite stream and applies them to values from the target stream's own history. The retrieved states are combined for an unchanged Transformer branch and updated through constrained gated writes; a block-form variant operates on block-level histories to control overhead. Across dense models from 0.1B to 1B parameters and a 7B sparse-MoE model, DAR consistently improves validation loss over standard residual Transformers and Attention Residuals. Routing ablations show that the gain cannot be explained by an additional stream or value projection alone. Representation and intervention analyses further show that reciprocal cross-stream selection preserves depth-wise diversity and avoids the redundancy or functional imbalance observed in alternative two-stream designs. △ Less

Submitted 21 July, 2026; originally announced July 2026.

Comments: 13 pages, 10 figures, and 8 tables

Task-Oriented Precoding for Edge Inference over Large-Scale MIMO Systems

Authors: Hongru Li, Zeyan Zhuang, Zixin Wang, Hengtao He, Shenghui Song, Jun Zhang, Khaled B. Letaief

Abstract: Future wireless networks are expected to support networked artificial intelligence (AI) services, where multiple devices transmit learned features to an edge server for distributed inference. This setting calls for task-oriented physical-layer optimization, where wireless transmission should preserve useful information for inference rather than only maximize the rate or reconstruct the transmitted… ▽ More Future wireless networks are expected to support networked artificial intelligence (AI) services, where multiple devices transmit learned features to an edge server for distributed inference. This setting calls for task-oriented physical-layer optimization, where wireless transmission should preserve useful information for inference rather than only maximize the rate or reconstruct the transmitted signals. A key physical-layer control variable is the multiple-input multiple-output precoder, which determines how device features are shaped and combined over wireless channels. Existing task-oriented precoding methods typically adapt the precoder to instantaneous channel state information at the transmitter (CSIT). However, in multi-device MIMO systems, acquiring the aggregate channel, feeding back CSI or optimized precoders, and reoptimizing across coherence blocks introduce substantial overhead. This paper develops a random-matrix-theoretic framework based on statistical CSIT that designs a slow-timescale precoder from channel covariance statistics and training-set feature statistics, without requiring instantaneous CSIT. We adopt maximal coding rate reduction (MCR${^2}$) to measure the class separability of the received features, yielding a task-aware utility for MIMO precoder design. Since this utility still depends on random small-scale fading, we derive a deterministic approximation that converts it into a fixed-point objective depending only on long-term statistics and large-system dimension ratios via random matrix theory. A projected block-coordinate ascent and successive convex approximation algorithm is developed to optimize this deterministic objective under per-device power constraints. Experiments on ModelNet10 verify the approximation and show that the proposed statistical precoder improves task-aware mode allocation and inference performance over competitive benchmarks. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Comments: 13 pages, 4 figures, submitted to IEEE for possible publication

Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, Evaluation, and Preference Alignment

Authors: Wentao Liu, Siyu Song, Xi Chen, Youjia Li, Xiaokun Wang, Min Ji, Ji Wang

Abstract: Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a coherent multi-turn arc. We present AnthroDial, a closed-loop framework that formulates anthropomorphic dialogue as a joint problem of system architecture, executable evaluation, and diagnostic alignment. It combines (1) a rol… ▽ More Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a coherent multi-turn arc. We present AnthroDial, a closed-loop framework that formulates anthropomorphic dialogue as a joint problem of system architecture, executable evaluation, and diagnostic alignment. It combines (1) a role-conditioned scheduled dialogue runtime with persona and scenario cards, long-term memory, virtual time, and single-draft message decisions; (2) an executable benchmark with an L0 validity gate, five per-turn dimensions, and five dialogue-level dimensions; and (3) a post-training pipeline that filters 16,436 scheduled-decision examples for SFT and applies GRPO with a cognitive-diagnostic, ZPD-aware reward. The reward maintains Kalman-filtered capability estimates for each behavioral dimension, upweights dimensions with larger capability deficits, and uses rollout scores as task-level ZPD matches to focus optimization on learnable weak skills. On a benchmark with 55 personas, 50 scenarios, 50 persona-scenario bindings, and 100 role-conditioned cases per model, we evaluate 16 systems spanning frontier baselines, open models, thinking/no-think variants, and SFT/RL ablations. The strongest non-trained baseline reaches 32.00% strict ACC, while Qwen3.6-27B-SFT+RL reaches 39.00% strict ACC and a 98.5 overall score. In the 9B no-think setting, SFT and RL improve strict ACC from 0.00% to 13.00% and 18.37%. These results show that anthropomorphic dialogue benefits when generation, evaluation, and reward shaping share the same behavioral dimensions. △ Less

Submitted 22 July, 2026; v1 submitted 19 July, 2026; originally announced July 2026.

Comments: 17 pages, 2 figures, 11 tables

Task-Oriented Communication with Hybrid-Precision Models

Authors: Songjie Xie, Wei Guo, Shenghui Song, Jun Zhang, Ying-Jun Angela Zhang, Khaled B. Letaief

Abstract: Edge inference has emerged as a promising solution for the proliferation of artificial intelligence (AI) services by deploying models at the network edge to circumvent cloud-routing latency. Existing edge inference approaches mainly focused on either cooperative inference to reduce latency or lightweight model design to fit resource-constrained devices. These solutions often address the communicat… ▽ More Edge inference has emerged as a promising solution for the proliferation of artificial intelligence (AI) services by deploying models at the network edge to circumvent cloud-routing latency. Existing edge inference approaches mainly focused on either cooperative inference to reduce latency or lightweight model design to fit resource-constrained devices. These solutions often address the communication and computation challenges separately, and thus struggle to achieve a balanced trade-off among transmission efficiency, on-device processing cost, and inference accuracy. To bridge this gap, this paper proposes a hybrid-precision task-oriented communication framework for edge inference to holistically balance communication, on-device computation, and utility. In this framework, a binarized front-end is deployed on the edge device to extract and transmit binary features via orthogonal frequency-division multiplexing (OFDM) signals, while a full-precision back-end on the edge server performs the final inference. To ensure model consistency, we introduce an on-device binarization method tailored for split inference and develop an integrated channel-aware transmission scheme featuring subcarrier-based feature calibration. Furthermore, a knowledge distillation (KD)-based training strategy, supported by specialized gradient estimators, is developed to optimize the end-to-end system and inherit semantic knowledge from a full-precision teacher model. Extensive experiments on the large-scale ImageNet dataset demonstrate the superiority of the proposed hybrid system. Our analysis confirms that this design achieves an optimal trade-off among communication efficiency, on-device computational cost, and inference accuracy, outperforming existing edge inference solutions. △ Less

Submitted 18 July, 2026; originally announced July 2026.

Handroid: Bridging Dexterous Hand and Humanoid

Authors: Ruogu Li, Chenyang Ma, Sikai Li, Zhenyu Wei, Yunchao Yao, Haochen Shi, C. Karen Liu, Shuran Song, Mingyu Ding

Abstract: Dexterous hands and humanoid robots are typically developed as distinct embodiments: the former enable contact-rich manipulation at the object scale, whereas the latter provide mobility and whole-body interaction in human-centered environments. We introduce \textbf{Handroid}, a desktop-scale dual-embodiment robot that integrates both capabilities within a single reconfigurable platform. Handroid r… ▽ More Dexterous hands and humanoid robots are typically developed as distinct embodiments: the former enable contact-rich manipulation at the object scale, whereas the latter provide mobility and whole-body interaction in human-centered environments. We introduce \textbf{Handroid}, a desktop-scale dual-embodiment robot that integrates both capabilities within a single reconfigurable platform. Handroid reuses one 27-DoF electromechanical body as either a dexterous hand or a desktop humanoid, measuring 0.33 m in height and 2.05 kg in weight. In the dexterous hand embodiment, 20 DoFs form an anthropomorphic hand closely matching the kinematic structure of the human hand. In the humanoid embodiment, the same articulated modules are reconfigured into a humanoid with a head, arms, and legs, including a 12-DoF lower-limb structure for locomotion and whole-body motion. Handroid further provides a unified control and learning framework supporting hand teleoperation, dexterous grasping, in-hand manipulation, humanoid locomotion, gait generation, and interactive motion authoring. We validate the platform through real-world dexterous manipulation, reinforcement-learning-based locomotion, keyframe motion deployment, and a long-horizon task involving embodiment reconfiguration, locomotion, docking, and dexterous pick-and-place. These results position Handroid as a compact and reproducible platform for advancing morphology-reconfigurable robotics and cross-embodiment robot learning. △ Less

Submitted 17 July, 2026; originally announced July 2026.

Comments: Project website: https://handroid.org

Mixture of Frames Policy: Multi-Frame Action Denoising for Bimanual Mobile Manipulation

Authors: Dian Wang, Jisang Park, Xiaomeng Xu, Han Zhang, Shuran Song, Jeannette Bohg

Abstract: Robotic manipulation is inherently multi-frame: local actions may be simple in an end-effector frame, while transport, upright-object handling, and whole-body coordination are better represented in a base-aligned frame. However, modern diffusion-based visuomotor policies typically commit to a single predefined action frame, forcing one denoiser to model action distributions that are often unnecess… ▽ More Robotic manipulation is inherently multi-frame: local actions may be simple in an end-effector frame, while transport, upright-object handling, and whole-body coordination are better represented in a base-aligned frame. However, modern diffusion-based visuomotor policies typically commit to a single predefined action frame, forcing one denoiser to model action distributions that are often unnecessarily complex in that frame. We propose Mixture of Frames Policy (MoF), a diffusion policy that performs synchronized action denoising across multiple coordinate frames. MoF maintains a single canonical diffusion state, re-expresses it in several task-relevant frames, applies frame-specialized denoisers, and fuses their noise predictions back in the canonical frame. To make this possible for intermediate noisy diffusion states, we introduce a column-based 6D rotation representation within an SE(3) action parameterization that supports exact, differentiable frame transformations without requiring noisy rotations to lie on the SO(3) manifold. Across nine simulated bimanual manipulation tasks, we show that the best action frame is task-dependent and that MoF improves over oracle frame selection and standard Mixture-of-Experts (MoE) baselines. We further evaluate MoF on two real-world bimanual mobile manipulation tasks, demonstrating that it outperforms all constituent single-frame baselines. Project homepage: https://mofpo.github.io △ Less

Submitted 13 July, 2026; originally announced July 2026.

Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists

Authors: Chuhan Shi, Xiaoquan Ren, Sicheng Song, Haobo Li, Rui Sheng, Yushi Sun

Abstract: Existing benchmarks for scientific data analysis evaluate LLMs primarily on code execution or workflow completion, overlooking that scientific analysis serves to support distinct types of scientific claims: hypothesis exploration, statistical inference, mechanistic explanation, each with different assumptions and validity criteria. We introduce SDABench, a benchmark that reorganizes evaluation aro… ▽ More Existing benchmarks for scientific data analysis evaluate LLMs primarily on code execution or workflow completion, overlooking that scientific analysis serves to support distinct types of scientific claims: hypothesis exploration, statistical inference, mechanistic explanation, each with different assumptions and validity criteria. We introduce SDABench, a benchmark that reorganizes evaluation around six capabilities (descriptive, exploratory, inferential, predictive, causal, and mechanistic) across five domains (Biology, Chemistry, Environment, Geography, Physics). SDABench comprises 527 real-data instances (SDA-Real) and 6000 synthetic instances (SDA-Synth), each in both multiple-choice and open-ended formats, constructed through an automated pipeline. Evaluating 15 representative LLMs, we find that models handle descriptive analysis well but degrade sharply on tasks requiring assumption selection, latent-process modeling, or mechanistic reasoning. SDABench further provides a five-stage error analysis framework that locates where LLMs fail: more advanced models more reliably identify the relevant scope and variables, but still struggle to select appropriate analytical procedures, model variable relationships, and draw valid conclusions. △ Less

Submitted 13 July, 2026; originally announced July 2026.

The First ChineseBabyLM Challenge: training data-efficient and cognitively plausible language models for Chinese

Authors: Siyuan Song, Zhiheng Qian, Yunhao Zhang, Linyang He, Xiaozhe Ji, Yingxin Lin, Hongao Zhu, Chongtian Shao, Chuhan Lang, Luan Li, Rui Wang, Renfen Hu, Shaonan Wang, Hai Hu

Abstract: This paper presents the first ChineseBabyLM Challenge, organized as part of NLPCC 2026. The challenge asked participants to train language models from scratch using no more than 102M Chinese words. The models were evaluated on three tracks: natural language understanding, cognitive alignment, and Hanzi knowledge. There were no restrictions on tokenizers, model architectures, or the number of train… ▽ More This paper presents the first ChineseBabyLM Challenge, organized as part of NLPCC 2026. The challenge asked participants to train language models from scratch using no more than 102M Chinese words. The models were evaluated on three tracks: natural language understanding, cognitive alignment, and Hanzi knowledge. There were no restrictions on tokenizers, model architectures, or the number of training epochs. Eighteen teams submitted 28 distinct models, generating 74 result files. The overall-winning team used a DeBERTa-v2 architecture and introduced an auxiliary pinyin-prediction objective during pretraining. Several submissions also explored curriculum-learning strategies and architectural innovations. Overall, the challenge provides a benchmark for advancing data-efficient and cognitively plausible approaches to Chinese language modeling. △ Less

Submitted 17 August, 2026; v1 submitted 12 July, 2026; originally announced July 2026.

Comments: 13 pages

Heterogeneity-Adaptive Diffusion Schrodinger Bridge for PET-Guided Whole-Body MRI Translation

Authors: Chengbo Wang, Jiacheng Yu, Linjie Bian, Ming Qi, Xiaosheng Liu, Tongtong Che, Jichang Zhang, Shuyu Li, Shaoli Song, Xiuying Wang

Abstract: While whole-body multimodal medical imaging scanners have been increasingly recognized for more effective medical applications, the excessive long acquisition time in PET-MR scanning is a major obstacle in more efficient clinical practice. Deep learning-based MRI translation provides a potential solution to reduce scan duration. However, current models often focus on specific anatomical regions an… ▽ More While whole-body multimodal medical imaging scanners have been increasingly recognized for more effective medical applications, the excessive long acquisition time in PET-MR scanning is a major obstacle in more efficient clinical practice. Deep learning-based MRI translation provides a potential solution to reduce scan duration. However, current models often focus on specific anatomical regions and face challenges for whole-body scans that consists of highly heterogeneous feature distributions mainly due to (1) different anatomical regions across whole-body, and (2) lesions or pathological tissues. This paper tackles the challenges through a novel Heterogeneity-Adaptive Diffusion Schrodinger Bridge (HA-DSB) framework. By explicitly modeling translation as stochastic transport between source and target distributions, HA-DSB incorporates region context embeddings derived from a vision-language model (VLM) to enable region-specific modeling. To enhance fidelity of the pathological tissue, lesion-aware metabolic prior from PET is integrated directly into the bridge dynamics through a dual-stage guidance mechanism. Specifically, a PET-guided noise modulation module adaptively scales spatial diffusion perturbations during the forward process, while PET features are leveraged during the reverse process to selectively amplify lesion-relevant structures via an attention mechanism. Experiments demonstrate the superiority of our method across different body regions in whole-body MRI translation and show improved translation quality in lesion areas under PET guidance. Our code is available at Github. △ Less

Submitted 8 July, 2026; originally announced July 2026.

Comments: Accepted at MICCAI 2026

HPR-SAM: Hierarchical Probabilistic Representation Learning for Prompt-free SAM-based Medical Image Segmentation

Authors: Yingzhen Hu, Yiheng Zhong, Keying Zhu, Zimu Zhang, Zihan Ye, Sifan Song, Jionglong Su, Xiaofeng Liu

Abstract: Prompt-free adaptation of the Segment Anything Model (SAM) has emerged as a promising paradigm for automatic medical image segmentation. Existing methods mainly focus on prompt generation, while overlooking that prompt quality is fundamentally constrained by the expressiveness of anatomical representations. However, deterministic prototypes or semantic tokens are insufficient to jointly capture gl… ▽ More Prompt-free adaptation of the Segment Anything Model (SAM) has emerged as a promising paradigm for automatic medical image segmentation. Existing methods mainly focus on prompt generation, while overlooking that prompt quality is fundamentally constrained by the expressiveness of anatomical representations. However, deterministic prototypes or semantic tokens are insufficient to jointly capture global anatomical priors, intra-structure diversity, and local structural reliability. To address this limitation, we propose the Hierarchical Probabilistic Representation (HPR) framework, which learns complementary anatomical representations through Distributional Anatomical Representation (DAR), Multi-component Anatomical Representation (MAR), and Local Reliability Representation (LRR), and integrates their predictions via Hierarchical Prediction Fusion (HPF) while remaining compatible with the original SAM decoder. Experiments on the Synapse, LA, and PROMISE12 datasets demonstrate that HPR-SAM achieves state-of-the-art performance on Synapse and the best performance under few-shot settings on LA and PROMISE12, validating the effectiveness of the proposed hierarchical probabilistic representation learning framework for prompt-free medical image segmentation. Code is available at https://anonymous.4open.science/r/HPR-SAM-E4AF. △ Less

Submitted 7 July, 2026; originally announced July 2026.

Comments: 9 pages, 4 figures

Conversational Human Audio-visual Talking Dialogue Generation

Authors: Junhao Song, Lluis Guasch, Xilin He, Zhongyu Yang, Yingfang Yuan, Weicheng Xie, Linlin Shen, Haijun Lin, Shizhe Liu, Wei Pang, Siyang Song

Abstract: Large-scale dyadic interactive audio-visual dialogue (DIAD) datasets provide fundamental data resources for developing humanoid interactive virtual agents and digital humans. However, collecting such data is time-consuming, expensive, and ethically sensitive. To address this, we propose CHAT, a new dyadic interactive audio-visual dialogue generation (DIADG) framework that generates diverse, paired… ▽ More Large-scale dyadic interactive audio-visual dialogue (DIAD) datasets provide fundamental data resources for developing humanoid interactive virtual agents and digital humans. However, collecting such data is time-consuming, expensive, and ethically sensitive. To address this, we propose CHAT, a new dyadic interactive audio-visual dialogue generation (DIADG) framework that generates diverse, paired, and mutually responsive speech-face dialogue clips from a single textual prompt. CHAT unifies large language models and talking face models with interactive audio and facial behaviour refinement modules, enabling the generation of aligned dyadic dialogue clips with diverse contents and facial identities. Experiments show that CHAT outperforms existing related methods designed for similar tasks under both objective and subjective evaluations. Moreover, our synthesised CHAT-AVD-50k dataset serves as effective pre-training data for downstream interactive head generation, consistently improving PerFRDiff and ReactDiff on REACT 2024. CHAT offers a scalable alternative to the costly and ethically sensitive collection of real dyadic interaction data. △ Less

Submitted 2 July, 2026; originally announced July 2026.

Comments: Accepted to ECCV 2026 as a main paper

Multi-Objective Exploration and Preference Optimization via Mutual Information

Authors: Hongyan Xie, Yikun Ban, Ruiyu Fang, Zixuang Huang, Deqing Wang, Jianxin Li, Shuangyong Song

Abstract: Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions. Current methods achieve this trade-off by training policies conditioned on preference vectors and leveraging online direct preference optimization. However, exploration uncertainty can cause the reward distributions of res… ▽ More Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions. Current methods achieve this trade-off by training policies conditioned on preference vectors and leveraging online direct preference optimization. However, exploration uncertainty can cause the reward distributions of responses generated under different preference vectors to overlap, and the generated responses may fail to effectively align with the corresponding preference vectors. In this paper, we propose Multi-Objective Exploration and Preference Optimization via Mutual Information (MI-EPO), an information-theoretic framework. It unifies multi-objective exploration and alignment by maximizing the joint conditional mutual information among generated responses, preference feedback, and preference vectors. By incorporating a probabilistic routing mechanism, MI-EPO naturally decomposes objective alignment and preference-aware exploration, encouraging the model to generate responses that are distinguishable and aligned with different preference conditions. Experiments on safe alignment and helpful assistant tasks show that MI-EPO significantly improves the alignment between generated responses and preference vectors, makes the outputs more controllable, and achieves stable trade-offs across multiple objectives. △ Less

Submitted 3 July, 2026; v1 submitted 1 July, 2026; originally announced July 2026.

Comments: Accepted at ECML/PKDD 2026

ROSA: A Robotics Foundation Model Serving System for Robot Factories

Authors: Wenqi Jiang, Jason Clemons, Rowland O'Flaherty, Hugo Hadfield, Alperen Degirmenci, Shuran Song, Yashraj Narang, Christos Kozyrakis

Abstract: Robotics foundation models (RFMs) are making general-purpose robots increasingly practical for factory deployments. While RFM serving systems are central to this vision, existing systems are largely shaped by a single-robot, single-model assumption: inference is treated as an edge-computing problem handled by an on-robot or dedicated nearby GPU, and the serving objective is to minimize the latency… ▽ More Robotics foundation models (RFMs) are making general-purpose robots increasingly practical for factory deployments. While RFM serving systems are central to this vision, existing systems are largely shaped by a single-robot, single-model assumption: inference is treated as an edge-computing problem handled by an on-robot or dedicated nearby GPU, and the serving objective is to minimize the latency of a single action model. In this paper, we propose ROSA, an RFM serving system for robot factories designed around three key principles. First, ROSA adopts shared GPU-pool serving, allowing a fleet of robots to access powerful server-class GPUs over the network in order to improve inference performance, battery duration, and GPU utilization. Second, ROSA provides a robotics-aware programming abstraction and system design that supports multi-model pipelines, per-task performance requirements, and failure handling. Third, ROSA uses factory-objective-driven scheduling to maximize SLO-qualified factory productivity rather than minimizing individual request latency. We implement ROSA on top of Ray Serve for distributed orchestration, with vLLM, PyTorch, and JAX as model-serving backends, and evaluate it on both real robots and synthetic large-scale workloads. The results show that ROSA improves factory productivity by up to 12.06x over conventional dedicated serving systems. △ Less

Submitted 1 July, 2026; originally announced July 2026.

GR2 Technical Report

Authors: Yufei Li, Zaiwei Zhang, Mingfu Liang, Kavosh Asadi, Jay Xu, Jimmy Kim, Chongyang Bai, Jieyi Zhang, Hongye Xie, Prachi Agrawal, Dian Yu, Tianyi Chen, Jean-Pascal Billaud, Garret Buell, Yongkang Zhu, Sachin Patil, Brooke Bian, Zhou Fang, Kevin Huang, Shiva Sudanagunta, Yuzhen Huang, Emma Lu, Chris O'Brien, Yang Song, Lihong Li , et al. (46 additional authors not shown)

Abstract: Industrial recommendation systems serve billions of users through a multi-stage funnel -- retrieval, early-stage ranking, and re-ranking -- where the final re-ranking step disproportionately shapes user engagement and downstream performance, particularly for carousel and grid display formats. Despite growing enthusiasm for Large Language Models (LLMs) in recommendation, three gaps hinder industria… ▽ More Industrial recommendation systems serve billions of users through a multi-stage funnel -- retrieval, early-stage ranking, and re-ranking -- where the final re-ranking step disproportionately shapes user engagement and downstream performance, particularly for carousel and grid display formats. Despite growing enthusiasm for Large Language Models (LLMs) in recommendation, three gaps hinder industrial adoption: (1) most efforts target retrieval and ranking, leaving re-ranking -- the stage closest to the final user experience -- largely underexplored; (2) LLMs are typically deployed zero-shot or via supervised fine-tuning, underutilizing the reasoning capabilities unlocked by reinforcement learning (RL) on verifiable rewards; (3) deployed catalogs index billions of items with non-semantic identifiers that lie outside any base-LLM vocabulary. We present GR2 (Generative Reasoning Re-Ranker), an end-to-end framework that combines (i) mid-training on semantic IDs produced by a tokenizer with >=99% uniqueness, (ii) reasoning-trace distilled from a stronger teacher via targeted prompting and rejection sampling, and (iii) RL with verifiable rewards purpose-built for re-ranking. To make GR2 resource-viable, we further (iv) introduce a context compressor that amortizes training cost, On-Policy Distillation (OPD) as a scalable alternative to SFT -- which we find collapses at industrial scale -- and reasoning distillation for low-latency serving. GR2 delivers +18.7% R@1, +7.1% R@3, and +9.6% N@3 over legacy baselines on industrial-scale traffic. We further find that reward design is critical in re-ranking: LLMs often hack rewards by preserving the incoming order or exploiting position bias, motivating conditional verifiable rewards as essential industrial components. △ Less

Submitted 3 July, 2026; v1 submitted 30 June, 2026; originally announced June 2026.

Comments: 18 pages, 10 figures

In-situ Indexing via Memristive Content-Addressable Memory

Authors: Bing Wu, Xueliang Wei, Shiyi Song, Yibo Liu, Jinpeng Liu, Wei Tong, Hao Tong, Yuchong Hu, Dan Feng

Abstract: Processing-in-Memory (PIM) is a proven paradigm for overcoming the ``memory wall". However, while data indexing is severely bottlenecked by this same wall, it remains unclear how indexing can effectively benefit from PIM's unique capabilities. We present PATH, an in-situ indexing architecture that bridges this gap by leveraging the massive parallelism and inherent data-movement of PIMs. Specifical… ▽ More Processing-in-Memory (PIM) is a proven paradigm for overcoming the ``memory wall". However, while data indexing is severely bottlenecked by this same wall, it remains unclear how indexing can effectively benefit from PIM's unique capabilities. We present PATH, an in-situ indexing architecture that bridges this gap by leveraging the massive parallelism and inherent data-movement of PIMs. Specifically, we first reformulate the fundamental indexing operations, namely Insert, Search, Update, and Delete, into highly parallel in-situ content-addressable memory operations executed directly within memory arrays. Taking hash indexes as a typical case, we elaborate how PATH breaks the inherent trade-off among memory accesses, load factor, and process latency in conventional hashing schemes. By adopting ultra-large logical buckets and in-memory moving, PATH virtually eliminates the cost of hash collision resolution and significantly reduces resizing overhead. Compared with state-of-the-art schemes, PATH achieves $4.7-7.8\times$ higher throughput, $>14.5\times$ lower tail latency, and $>61.4\%$ fewer memory accesses under insertions, laying a scalable foundation for next-generation data-centric computing. △ Less

Submitted 30 June, 2026; originally announced June 2026.

Comments: 15 pages

Robustness of Robotic Manipulation: Foundations and Frontiers

Authors: Yifei Dong, Zhanyi Sun, Lujie Yang, Manuel Baum, Kei Ikemura, Shuran Song, Florian T. Pokorny, Xianyi Cheng

Abstract: Humans and animals exhibit remarkable robustness in physical manipulation, yet robots remain far behind. Progress toward human-level manipulation robustness is hindered by the absence of a unified and systematic understanding: different subfields frame robustness in distinct ways, often leaving the concept ambiguous and limiting deeper analysis as well as communication across research areas. This… ▽ More Humans and animals exhibit remarkable robustness in physical manipulation, yet robots remain far behind. Progress toward human-level manipulation robustness is hindered by the absence of a unified and systematic understanding: different subfields frame robustness in distinct ways, often leaving the concept ambiguous and limiting deeper analysis as well as communication across research areas. This paper presents a systematic study of manipulation robustness. We begin with a formal definition, characterizing robustness as the degree to which a manipulation system can achieve its goal in the presence of uncertainty and variation. Building on this definition, we introduce general formulations of manipulation robustness from probabilistic and control-theoretic perspectives. We then synthesize the guiding principles and concrete mechanisms of manipulation robustness across perception, planning, control, policy learning, and hardware, illustrating each mechanism through representative works, including foundational and recent studies. In addition, we revisit existing metrics and evaluation methods for quantifying manipulation robustness. Finally, we distill broader lessons for designing robust manipulation systems and discuss open problems and future directions toward achieving human-level robustness in robotic manipulation. △ Less

Submitted 30 June, 2026; originally announced June 2026.

Multisensory Continual Learning: Adapting Pretrained Visuomotor Policies to Force

Authors: Jaden Clark, Changhao Wang, Yihuai Gao, Seongheon Hong, Hojung Choi, Mark Cutkosky, Yifan Hou, Shuran Song

Abstract: Robot manipulation often relies on sensory feedback beyond vision, particularly in contact-rich settings where force, tactile, or audio signals reveal interaction states that are not directly observable from images. However, these modalities are often hardware- and task-specific, and large-scale multisensory robot datasets remain scarce. As a result, it is impractical to pretrain policies with eve… ▽ More Robot manipulation often relies on sensory feedback beyond vision, particularly in contact-rich settings where force, tactile, or audio signals reveal interaction states that are not directly observable from images. However, these modalities are often hardware- and task-specific, and large-scale multisensory robot datasets remain scarce. As a result, it is impractical to pretrain policies with every sensor they may encounter. We study multisensory continual learning: adapting a pretrained robot policy to new tasks with newly introduced modalities while preserving performance under the original sensor suite. We propose MultiSensory World Model (MuSe), which incorporates limited multisensory data into pretrained vision-only policies through multi-stage fusion, multisensory future prediction, and experience replay over pretraining data. We instantiate MuSe by augmenting a pretrained vision-only policy with force-torque sensing and evaluate it on real-world manipulation tasks. Our experiments show that MuSe performs strongly on contact-rich finetuning tasks while preserving, and in some cases improving, performance on the original pretraining tasks. These results suggest that a modest multisensory dataset can improve general robot capabilities beyond the finetuning distribution. Project website: https://jadenvc.github.io/multisensory-continual-learning/ △ Less

Submitted 5 July, 2026; v1 submitted 29 June, 2026; originally announced June 2026.

Behavior Prompting Policy: Demonstrations as Prompts for Manipulation

Authors: Austin Patel, Ben Pekarek, Joel Enrique Castro Hernandez, Shuran Song

Abstract: We study behavior prompting, a paradigm that enables robots to perform new tasks at inference time given a single human demonstration, which we call a behavior prompt. To enable this capability, we present contributions in algorithm, data, and evaluation. For algorithm, we introduce Behavior Prompting Policy (BPP), an in-context visuomotor architecture that translates the behavior prompt and the c… ▽ More We study behavior prompting, a paradigm that enables robots to perform new tasks at inference time given a single human demonstration, which we call a behavior prompt. To enable this capability, we present contributions in algorithm, data, and evaluation. For algorithm, we introduce Behavior Prompting Policy (BPP), an in-context visuomotor architecture that translates the behavior prompt and the current observation into robot actions. For data, we identify that task diversity is the primary driver of the prompting capability and introduce iPhUMI, a handheld manipulation interface for collecting diverse training data. For evaluation, we introduce DrawAnything and LIBERO-Gen to evaluate test-time adaptation to unseen drawing and tabletop manipulation tasks. We also demonstrate that iPhUMI serves as a practical interface for specifying behavior prompts at test time, enabling a human to command a robot via a single demonstration to complete known tasks or to define new robot capabilities. Altogether, behavior prompting provides a flexible and scalable way to teach robots new skills without the need for expensive fine-tuning. Our project website is located at https://behavior-prompting.github.io/ . △ Less

Submitted 29 June, 2026; originally announced June 2026.

RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation

Authors: Zixuan Zhang, Yuqi Chen, Junjie Gao, Siyuan Song, Yongzhou Pan, Beichen Wang, Mir Feroskhan

Abstract: Image-goal navigation is a key challenge in embodied robotics, where an agent must reach a target specified solely by a goal image. While existing reinforcement learning approaches map perceptual observations directly to actions, they struggle to model long-horizon dependencies, often leading to suboptimal trajectories. To address this limitation, we propose RoamFlow, a generative navigation frame… ▽ More Image-goal navigation is a key challenge in embodied robotics, where an agent must reach a target specified solely by a goal image. While existing reinforcement learning approaches map perceptual observations directly to actions, they struggle to model long-horizon dependencies, often leading to suboptimal trajectories. To address this limitation, we propose RoamFlow, a generative navigation framework that leverages MeanFlow to predict the average velocity field for trajectory synthesis, enabling efficient few-step generation and reducing inference latency. We further adopt a two-stage training strategy that combines expert imitation for stable initialization with reinforcement learning for task-specific policy refinement. Extensive experiments in both Habitat simulation and real-world robotic platforms demonstrate that RoamFlow achieves efficient inference while maintaining strong navigation performance under real-time constraints. △ Less

Submitted 29 June, 2026; originally announced June 2026.

MTD-Map: Single-Stage Long-Term LiDAR Map Maintenance Framework via Mixture Transition Distribution

Authors: TaeYoung Kim, Gilhwan Kang, Tae Ihn Kim, Seungwon Song, Hun Keon Ko

Abstract: While robust map maintenance has advanced significantly, existing studies have focused on specific tasks, especially dynamic object removal or change detection. In this paper, we take a holistic view of the map maintenance problem and propose MTD-Map, a single-stage framework that handles both dynamic object removal and change detection without separate task-specific modules. MTD-Map employs an ex… ▽ More While robust map maintenance has advanced significantly, existing studies have focused on specific tasks, especially dynamic object removal or change detection. In this paper, we take a holistic view of the map maintenance problem and propose MTD-Map, a single-stage framework that handles both dynamic object removal and change detection without separate task-specific modules. MTD-Map employs an explicit representation that compactly encodes the direction and duration of occupancy transitions through Mixture Transition Distribution (MTD) modeling. We develop a recursive MTD formulation that encodes historical occupancy patterns into an augmented state to capture high-order temporal dependencies. Furthermore, a stability-driven adaptive strategy balances noise suppression with the preservation of quasi-static structures. Extensive experiments verify that MTD-Map robustly removes dynamic objects and achieves competitive change detection performance, subsequently reducing computational costs. Our project page is available at: https://taeyoung96.github.io/mtd_map/. △ Less

Submitted 28 June, 2026; originally announced June 2026.

Comments: 8 pages, Accepted to IROS 2026

SatSplat: Geometrically-Accurate Gaussian Splatting for Satellite Imagery

Authors: Shuang Song, Jiyong Kim, Rongjun Qin

Abstract: High-resolution satellite imagery demands 3D reconstruction methods that deliver both speed and geometric accuracy. Recent adaptations of 3D Gaussian Splatting (3DGS) to satellite imagery demonstrate strong efficiency, but reconstruction quality often degrades under diverse illumination across multi-date, high-altitude acquisitions (with small intersection angles), limiting applicability to remote… ▽ More High-resolution satellite imagery demands 3D reconstruction methods that deliver both speed and geometric accuracy. Recent adaptations of 3D Gaussian Splatting (3DGS) to satellite imagery demonstrate strong efficiency, but reconstruction quality often degrades under diverse illumination across multi-date, high-altitude acquisitions (with small intersection angles), limiting applicability to remote sensing and vision tasks. We present SatSplat, the first framework to adapt 2D Gaussian Splatting (2DGS) to satellite photogrammetry, with online camera adjustment. We approximate satellite cameras with an affine model and learn a minimal delta parameterization for in-splat camera refinement from dense observations. The formulation is implemented with a 2DGS scene representation. To handle time-varying shadows and illumination changes, we integrate geometric shadow mapping and per-camera color correction during training. Across the evaluated DFC2019 and IARPA2016 benchmark sites, SatSplat achieves strong geometric accuracy while significantly outperforming prior 3DGS-based baselines. On our processed DFC2019 benchmark, SatSplat reduces mean absolute error by 11.93% and peak video memory by 31% relative to the previous state of the art. Our approach enables large-scale digital surface modeling with practical computational efficiency. The project page is available at https://gdaosu.github.io/satsplat/. △ Less

Submitted 26 June, 2026; originally announced June 2026.

Comments: Photogrammetric Engineering & Remote Sensing

SatSplatDiff: Geometry-preserving generative refinement for high-fidelity satellite Gaussian Splatting

Authors: Jiyong Kim, Shuang Song, Ronjgun Qin

Abstract: Gaussian Splatting has been recently explored for satellite 3D reconstruction, demonstrating flexibility and efficiency in representing radiometrically diverse satellite scenes. However, the limited top viewpoint of satellite imagery results in insufficient supervision on building facades, leaving surface holes and degraded visual fidelity. Generative refinement, which leverages pretrained generat… ▽ More Gaussian Splatting has been recently explored for satellite 3D reconstruction, demonstrating flexibility and efficiency in representing radiometrically diverse satellite scenes. However, the limited top viewpoint of satellite imagery results in insufficient supervision on building facades, leaving surface holes and degraded visual fidelity. Generative refinement, which leverages pretrained generative priors to iteratively refine and update the rendered images used as supervision targets, has recently been investigated to improve the visual fidelity of Gaussian-rendered images. However, since these models refine each view independently, the resulting images can generate hallucinations and break photo-consistency, leading to geometric degradation. To address these limitations, we propose SatSplatDiff, which aims to minimize geometric degradation prevalent in generative refinement. Building on photogrammetric DSM initialization and 2DGS-based shadow casting established in our prior work SatSplat, we first introduce monocular depth supervision and multi-scale geometric refinement to establish a geometrically accurate and well-regularized surface representation. We then apply shadow-guided generative refinement, where geometrically calculated shadow maps guide the Gaussians to maintain consistency with the underlying geometry, improving visual fidelity while reducing geometric degradation. Extensive evaluations on the IARPA2016 and DFC2019 datasets demonstrate state-of-the-art performance, reducing geometric MAE by up to 18% and improving visual fidelity (FID-CLIP) by 28-45% over existing baselines. Our method delivers up to 5x resolution enhancement with minimal hallucination and sensor-consistent appearance, demonstrating seamless cross-tile consistency and strong scalability for large-scale reconstruction. Source code is available at https://github.com/GDAOSU/SatSplatDiff △ Less

Submitted 26 June, 2026; v1 submitted 25 June, 2026; originally announced June 2026.

Comments: 23 pages, 15 figures

MedSWFlow: An Open-Source LLM Workflow for Drafting Medical Social Work Case Plans

Authors: Yulin Mao, Shiyu Li, Shuping Song, Yuling Zhang, Yajun Song

Abstract: We present MedSWFlow, an open-source, model-agnostic LLM workflow for drafting medical social work case plans. The framework translates professional case-planning tasks into six stages: assessment, problem analysis, goal setting, intervention planning, risk anticipation, and planned effect evaluation. Drawing on established social work and behavioral frameworks, MedSWFlow standardizes case inputs,… ▽ More We present MedSWFlow, an open-source, model-agnostic LLM workflow for drafting medical social work case plans. The framework translates professional case-planning tasks into six stages: assessment, problem analysis, goal setting, intervention planning, risk anticipation, and planned effect evaluation. Drawing on established social work and behavioral frameworks, MedSWFlow standardizes case inputs, builds structured case profiles, and generates reviewable assessment forms and service plans through staged prompting. The system is released as an open-source research framework for reproducible case-plan generation across LLM providers. Outputs are intended as practitioner-reviewed drafts rather than final service decisions. Source code: https://github.com/santhiyacw-droid/MedSWFlow/tree/main. △ Less

Submitted 25 June, 2026; originally announced June 2026.

Comments: 26pages, 8tables, 2figuers

ACM Class: I.2.7

TAVR-VLM: Risk-Conditioned Causal Grounding for Hallucination-Resistant Report Generation

Authors: Zhixiang Lu, Xiwei Liu, Sifan Song, Changkai Ji, Anh Nguyen, Jionglong Su, Imran Razzak, Jinfeng Wang

Abstract: Transcatheter Aortic Valve Replacement (TAVR) planning requires meticulous multimodal reasoning. However, adapting Multimodal Large Language Models (MLLMs) to this high-stakes domain is severely impeded by diagnostic hallucinations, where generated text lacks anatomical grounding. To address this, TAVR-VLM is introduced: a novel framework featuring Risk-Conditioned Causal Grounding Attention (R-CG… ▽ More Transcatheter Aortic Valve Replacement (TAVR) planning requires meticulous multimodal reasoning. However, adapting Multimodal Large Language Models (MLLMs) to this high-stakes domain is severely impeded by diagnostic hallucinations, where generated text lacks anatomical grounding. To address this, TAVR-VLM is introduced: a novel framework featuring Risk-Conditioned Causal Grounding Attention (R-CGA) that instantiates a model-internal ``Risk $\rightarrow$ Region $\rightarrow$ Word'' structural grounding pathway. R-CGA compresses multimodal inputs into a causal risk bottleneck, purifying dense visual features into a global risk mask. During autoregressive generation, a support-projected causal consistency objective constrains token-level grounding within the risk-defined support mask. Evaluated on $\text{M}^3\text{TAVR}$, a comprehensive 1,482-patient cohort, TAVR-VLM establishes a new state-of-the-art. It achieves an AUROC of 0.896, boosts CIDEr to 0.936, and drastically reduces the hallucination rate to 8.1\%, thereby improving interpretability for evidence-based surgical AI. △ Less

Submitted 25 June, 2026; originally announced June 2026.

TESLA-for-5G: Broadcast Authentication for 5G Networks Using TESLA

Authors: Subin Song, Michael K. Reiter, Taekyoung Kwon

Abstract: 5G base stations broadcast unauthenticated system information (SI) that every user equipment (UE) reads during cell selection. This enables attackers to broadcast forged SI from a fake base station (FBS), deceiving UEs into camping on it. Prior approaches require UEs to authenticate System Information Block 1 (SIB1) using digital signatures. This necessitates computation-heavy verification for eve… ▽ More 5G base stations broadcast unauthenticated system information (SI) that every user equipment (UE) reads during cell selection. This enables attackers to broadcast forged SI from a fake base station (FBS), deceiving UEs into camping on it. Prior approaches require UEs to authenticate System Information Block 1 (SIB1) using digital signatures. This necessitates computation-heavy verification for every SIB1 reception, imposing a significant burden on resource-constrained UEs. We propose TESLA-for-5G (TF5), a broadcast authentication protocol for 5G SIB1 that combines TESLA with GG09 Schnorr-like identity-based signatures (IBS). In the steady state, TF5 enables UEs to authenticate each SIB1 message using a symmetric MAC and delayed key disclosure, eliminating the need for per-message digital signatures. Initial trust is bootstrapped during cell entry using a lightweight GG09 IBS over the TESLA parameters, avoiding certificate distribution overhead. We formally verify TF5 in Tamarin under a Dolev-Yao adversary and demonstrate its favorable computation, communication, and storage costs through both an implementation on the OpenAirInterface 5G stack and trace-driven analysis. △ Less

Submitted 24 June, 2026; originally announced June 2026.

Comments: 20 pages, 8 tables, 2 algorithms, no figures

DKVE: Decentralized Key Validation for End-to-End Encrypted Messaging

Authors: Subin Song, Taekyoung Kwon

Abstract: End-to-end encrypted messaging systems depend on authentic public key distribution to prevent man-in-the-middle (MitM) attacks. Current solutions present a stark trade-off: out-of-band (OOB) verification provides strong security but lacks scalability for large contact lists, while key transparency (KT) systems enable automated verification at high storage costs and operational complexity. We pro… ▽ More End-to-end encrypted messaging systems depend on authentic public key distribution to prevent man-in-the-middle (MitM) attacks. Current solutions present a stark trade-off: out-of-band (OOB) verification provides strong security but lacks scalability for large contact lists, while key transparency (KT) systems enable automated verification at high storage costs and operational complexity. We propose DKVE, a protocol that validates public keys through privacy-preserving cross-validation within users' social graphs. When obtaining a contact's public key from a key server, clients query mutual contacts to verify they hold the same key, combining Oblivious Pseudorandom Functions (OPRF) and Oblivious Key-Value Stores (OKVS) to preserve privacy of both queries and contact lists. DKVE employs a Sequential Probability Ratio Test (SPRT) to aggregate responses and detect server misbehavior with user-configurable error bounds. We evaluate DKVE through simulations on real social network datasets, demonstrating DKVE can detect MitM attacks with exceeding 97% for strong-to-moderate-tie networks. The remaining 3% of cases require validation through alternative methods such as KT and OOB verification. Our proof-of-concept implementation confirms feasibility for background operation on commodity hardware, in terms of the latency and bandwidth. As DKVE can reduce the frequency of KT queries by two orders of magnitude, it enables fundamental architectural shifts: KT directories can migrate from fast but space-inefficient Merkle trees to space-efficient data structures like RSA accumulators. While DKVE cannot replace existing methods entirely -- suffering from bootstrapping problems and degraded performance on weak-tie networks -- it provides a practical complementary key validation mechanism, making secure messaging more deployable for billion-user systems. △ Less

Submitted 24 June, 2026; originally announced June 2026.

Comments: 20 pages, 4 figures, 5 tables

SupplyNet: Supporting Visual Exploratory Learning in Supply Chain via Contextual Multi-Agent Simulation

Authors: Yanjia Li, Kelcy Kexin Han, Tianrui Hu, Yi-Fan Cao, Huamin Qu, Sicheng Song

Abstract: Simulation has long supported supply chain management instruction by letting learners observe network behavior and test decision strategies. Recent progress in LLM-driven agents opens new possibilities for richer, more adaptive simulations, but many existing systems still present abstract, opaque data that overwhelms learners and discourages active exploration. We introduce \textit{SupplyNet}, a g… ▽ More Simulation has long supported supply chain management instruction by letting learners observe network behavior and test decision strategies. Recent progress in LLM-driven agents opens new possibilities for richer, more adaptive simulations, but many existing systems still present abstract, opaque data that overwhelms learners and discourages active exploration. We introduce \textit{SupplyNet}, a gamified visual simulation system built on a contextual graph-based LLM multi-agent framework that models interdependent supply chain dynamics and provides responsive feedback through tiered challenges. \textit{SupplyNet} turns the simulation into a manipulable decision space by integrating an interactive network view of system state, a branching timeline for "what-if" exploration and comparison, and a task-oriented analysis console for structured performance breakdowns. Together, these visual components support counterfactual exploration, causal tracing, and comparative reasoning about outcomes. A user study suggests that \textit{SupplyNet} increases engagement and supports users' perceived understanding of supply chain dynamics, highlighting the potential of pairing contextual multi-agent simulation with visualization to advance operational comprehension. △ Less

Submitted 23 June, 2026; originally announced June 2026.

Comments: 25 pages, 7 figures

PanoVine: Whole-Body Visuomotor Control for Soft Growing Vine Robot

Authors: Yimeng Qin, Xiaomeng Xu, William Heap, Aditi Oak, Shuran Song, Allison Okamura

Abstract: Vine robots, a class of soft, growing robots, are suitable for navigating complex and confined environments due to their compliant bodies and self-supporting growth mechanism. However, hysteresis, tether interactions, and deformations make them difficult to predict and model, which in turn limits the effectiveness of conventional planning and control approaches. In this work, we present a data-dri… ▽ More Vine robots, a class of soft, growing robots, are suitable for navigating complex and confined environments due to their compliant bodies and self-supporting growth mechanism. However, hysteresis, tether interactions, and deformations make them difficult to predict and model, which in turn limits the effectiveness of conventional planning and control approaches. In this work, we present a data-driven, vision-based control framework for the first autonomous vine robot system. Our system integrates 19 cameras distributed along the robot's body to provide comprehensive feedback of both the robot state and the surrounding environment. Using this rich whole-body vision feedback, we train an end-to-end visuomotor policy from demonstrations for closed-loop autonomous control in complex environments. The policy efficiently aggregates information from distributed sensing while maintaining robustness to inaccurate robot states and actuation. Experimental results demonstrate that the learned policy enables robust navigation and manipulation in challenging scenarios, including steering through branched structures, climbing up slopes, traversing unsupported terrain, reaching objects precisely, and maneuvering through confined spaces and obstacles. Project website https://panovine-bot.github.io △ Less

Submitted 23 June, 2026; v1 submitted 22 June, 2026; originally announced June 2026.

FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model

Authors: Yuhwan Jeong, Hyeonseong Kim, Daehyun We, Seonkyu Song, Jinnyeong Yang, Hyun-Kurl Jang, Youngho Yoon, Kuk-Jin Yoon

Abstract: Synthetic data for autonomous driving is surging, powered by diffusion models that promise scalable scene generation. Yet key obstacles remain, as enforcing multi-view and temporal consistency often relies on backbone fine-tuning or added layers, which erodes pre-trained knowledge and weakens text alignment. Models also stay close to the training distribution, struggling under adverse weather and… ▽ More Synthetic data for autonomous driving is surging, powered by diffusion models that promise scalable scene generation. Yet key obstacles remain, as enforcing multi-view and temporal consistency often relies on backbone fine-tuning or added layers, which erodes pre-trained knowledge and weakens text alignment. Models also stay close to the training distribution, struggling under adverse weather and unseen configurations, and fidelity favors frequent over rare classes. We address these gaps with FrozenDrive, a controllable generative framework that preserves a pretrained diffusion models knowledge while achieving strong consistency. FrozenDrive conditions on rich driving-stack signals and text prompts, and introduces knowledge-preserving spatio-temporal attention to impose cross-view alignment and temporal coherence in a single pass within a parameter-free frozen diffusion backbone. An additional object-focused constraint improves per-object fidelity for rare categories. Without any weather- or scene-specific fine-tuning, our model synthesizes globally coherent multi-view driving scenes from text, particularly under adverse and rare conditions, and surpasses prior baselines. On nuScenes, FrozenDrive augmented data significantly improves AD models performance, especially at night and in rain, demonstrating stronger robustness when trained with our scenario-targeted data. △ Less

Submitted 18 June, 2026; originally announced June 2026.

Comments: Accepted to ECCV 2026

DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient Finetuning

Authors: Calvin Luo, Chen Sun, Shuran Song

Abstract: A natural recipe for intelligent robotic decision-making is initializing from pretrained generative control policies, which have summarized offline experience, and adapting them to self-collected online experience. We present DF-ExpEnse, an exploration technique that improves the quality of online experience collection, thus increasing finetuning sample-efficiency. DF-ExpEnse leverages the multimo… ▽ More A natural recipe for intelligent robotic decision-making is initializing from pretrained generative control policies, which have summarized offline experience, and adapting them to self-collected online experience. We present DF-ExpEnse, an exploration technique that improves the quality of online experience collection, thus increasing finetuning sample-efficiency. DF-ExpEnse leverages the multimodal modeling capabilities of the generative control policy to create an expressive and tractably evaluatable candidate set. It then utilizes an ensemble of critics to identify the action that best balances quality with high exploration interest. In fleet settings, DF-ExpEnse further enables cross-agent communication to facilitate collaborative exploration as a group. DF-ExpEnse can be seamlessly integrated with existing strategies that finetune pretrained generative control policies via reinforcement learning. We experimentally validate consistent sample-efficiency benefits through DF-ExpEnse across a variety of manipulation and locomotion tasks, compared to default finetuning and alternative action selection schemes. Project can be found at https://df-expense.github.io. △ Less

Submitted 17 June, 2026; originally announced June 2026.

Comments: ICML 2026

One Demo is Worth a Thousand Trajectories: Action-View Augmentation for Visuomotor Policies

Authors: Chuer Pan, Litian Liang, Dominik Bauer, Eric Cousineau, Benjamin Burchfiel, Siyuan Feng, Shuran Song

Abstract: Visuomotor policies for manipulation have demonstrated remarkable potential in modeling complex robotic behaviors, yet minor alterations in the robot's initial configuration and unseen obstacles easily lead to out-of-distribution observations. Without extensive data collection effort, these result in catastrophic execution failures. In this work, we introduce an effective data augmentation framewo… ▽ More Visuomotor policies for manipulation have demonstrated remarkable potential in modeling complex robotic behaviors, yet minor alterations in the robot's initial configuration and unseen obstacles easily lead to out-of-distribution observations. Without extensive data collection effort, these result in catastrophic execution failures. In this work, we introduce an effective data augmentation framework that generates visually realistic fisheye image sequences and corresponding physically feasible action trajectories from real-world eye-in-hand demonstrations, captured with a portable parallel gripper with a single fisheye camera. We introduce a novel Gaussian Splatting formulation, adapted to wide FoV fisheye cameras, to reconstruct and edit the 3D scene with unseen objects. We utilize trajectory optimization to generate smooth, collision-free, view-rendering-friendly action trajectories and render visual observations from corresponding novel views. Comprehensive experiments in simulation and the real world show that our augmentation framework improves the success rate for various manipulation tasks in both the same scene and the augmented scene with obstacles requiring collision avoidance. △ Less

Submitted 17 June, 2026; originally announced June 2026.

Comments: Project website: https://chuerpan.com/1001-demos.github.io/. Published at CoRL 2025

Journal ref: Proceedings of The 9th Conference on Robot Learning, PMLR 305:3902-3914, 2025

Written by AI, Managed by AI: Semantic Space Control and Index Sickness Elimination Across 391 Consecutive Sessions

Authors: Hui Zhang, Shuren Song

Abstract: The prevailing engineering intuition for addressing conceptual drift in long-horizon LLM collaboration is to trade more formal constraints for more reliable outputs -- designing symbolic identifier systems, accumulating defensive rules in System Prompts, expanding context windows. Our engineering record shows that in long-horizon settings, this direction may produce effects contrary to design inte… ▽ More The prevailing engineering intuition for addressing conceptual drift in long-horizon LLM collaboration is to trade more formal constraints for more reliable outputs -- designing symbolic identifier systems, accumulating defensive rules in System Prompts, expanding context windows. Our engineering record shows that in long-horizon settings, this direction may produce effects contrary to design intent. Using action research methods in a real software project (Bang-v3) spanning approximately one month and 391 collaborative sessions, we document and analyze the failure process of these strategies. When the symbolic system exceeds a complexity threshold, LLMs do not become more accurate -- instead, they abandon genuine understanding of business semantics, retreat to self-referential reasoning within the symbolic layer, and generate outputs that appear internally consistent but are physically disconnected from reality. We name this failure pattern "Index Sickness," and its canonical manifestation "Phantom Legislation." We name the underlying principle the "Pang Principle (Semantic Vitality Law)": natural language carrying explicit purpose conveys far greater information quality than symbolic expression. From this, we design and validate its physical engineering mechanism: "Baseline-Log Physical Separation." In the same project, this mechanism reduced AI Instructions volume by ~75%, and across the subsequent ~150 sessions, no recurrence of Index Sickness was observed. A bilingual companion version (Chinese) is included as supplementary material. △ Less

Submitted 19 June, 2026; v1 submitted 17 June, 2026; originally announced June 2026.

Comments: 22 pages, 2 tables, 1 figure. Action research. Bilingual submission (Chinese companion version included as supplementary). Submitted to ICSE 2027 IOR track

ACM Class: D.2.9; H.5.2; I.2.7

AdaPT: Adaptive Lesson Plan Transformer for Cross-Regional and Differentiated Instruction

Authors: Yanjie Zhang, Jiajun Zhu, Minyu Wu, Huamin Qu, Sicheng Song

Abstract: Due to educational inequality, high-quality lesson plans often mismatch the needs of disparate educational contexts. Teachers typically modify existing lesson plans to fit new contexts, but current tools instead focus on generating content from scratch, creating additional workload. Moreover, a critical gap remains in supporting teachers to quickly adapt to new learning profiles. To bridge these g… ▽ More Due to educational inequality, high-quality lesson plans often mismatch the needs of disparate educational contexts. Teachers typically modify existing lesson plans to fit new contexts, but current tools instead focus on generating content from scratch, creating additional workload. Moreover, a critical gap remains in supporting teachers to quickly adapt to new learning profiles. To bridge these gaps, we present AdaPT, a system leverages LLMs to support transformation of existing lesson plans for cross-regional and differentiated instruction. AdaPT features an interactive interface that allows teachers to input student profiles, offers structured lesson representation, provides explanations for lesson-plan transformations, automatically adapts lesson content for new contexts, and supports iterative, teacher-in-the-loop refinement. We evaluated AdaPT through a user study with 9 teachers and an expert evaluation with 3 specialists. Results show that AdaPT supports workflows of teachers and offers a promising pathway toward promoting educational equity. △ Less

Submitted 16 June, 2026; originally announced June 2026.

Agentic Discovery of Non-Canonical Antimicrobial Peptides with AMPGAN v3

Authors: Jay Jung, Xiaohan Zhang, Shenghan Song, Mahmoud Sayedahmed, Chijian Xiang, Yunong Xu, Ahmed AbdelKhalek, Severin T. Schneebeli, Matthew J. Wargo, Jianing Li, Safwan Wshah

Abstract: Antimicrobial resistance causes to over a million deaths annually. Antimicrobial peptides (AMPs) are a promising solution, but generative AMP models are not yet ready to design peptides with non-natural amino acids and/or chemical modifications, which are essential for real-world peptide drugs. We present AMPGAN v3, a multi-objective conditional GAN that expands the generative vocabulary to D-amin… ▽ More Antimicrobial resistance causes to over a million deaths annually. Antimicrobial peptides (AMPs) are a promising solution, but generative AMP models are not yet ready to design peptides with non-natural amino acids and/or chemical modifications, which are essential for real-world peptide drugs. We present AMPGAN v3, a multi-objective conditional GAN that expands the generative vocabulary to D-amino acids and N/C-terminus modifications such as amidation. By separating adversarial and activity-aware supervision across two specialized discriminators, AMPGAN v3 substantially improves training stability and outperforms prior generative AMP models on external classifiers. We validated five candidates spanning three structural classes in vitro; two showed activity against Gram-positive strains, with the best candidate reaching MIC 8 μg/mL against B. subtilis. To support downstream curation, we further present PepCraft, a multi-agent framework for end-to-end AMP discovery in which a Planning Agent orchestrates specialized executors for generation, filtering, and verification. Its prioritization recommendations align with our in vitro outcomes. Together, these contributions let us examine, on a small but real scale, how generative and agentic AI compose in therapeutic peptide discovery. Code: https://github.com/marszzibros/AMPGANv3 △ Less

Submitted 15 June, 2026; originally announced June 2026.

Comments: Presented at the GenBio Workshop, ICML 2026