Showing 1–50 of 224 results for author: Wu, A

Nebula: Enable City-Scale 3D Gaussian Splatting in Virtual Reality via Collaborative Rendering and Accelerated Stereo Rasterization

Authors: He Zhu, Zheng Liu, Xingyang Li, Anbang Wu, Jieru Zhao, Fangxin Liu, Yiming Gan, Jingwen Leng, Yu Feng

Abstract: 3D Gaussian splatting (3DGS) has drawn significant attention in the architectural community recently. However, current architectural designs often overlook the 3DGS scalability, making them fragile for extremely large-scale 3DGS. Meanwhile, the VR bandwidth requirement makes it impossible to deliver high-fidelity and smooth VR content from the cloud. We present Nebula, a coherent acceleration fr… ▽ More 3D Gaussian splatting (3DGS) has drawn significant attention in the architectural community recently. However, current architectural designs often overlook the 3DGS scalability, making them fragile for extremely large-scale 3DGS. Meanwhile, the VR bandwidth requirement makes it impossible to deliver high-fidelity and smooth VR content from the cloud. We present Nebula, a coherent acceleration framework for large-scale 3DGS collaborative rendering. Instead of streaming videos, Nebula streams intermediate results after the LoD search, reducing 1925% data communication between the cloud and the client. To further enhance the motion-to-photon experience, we introduce a temporal-aware LoD search in the cloud that tames the irregular memory access and reduces redundant data access by exploiting temporal coherence across frames. On the client side, we propose a novel stereo rasterization that enables two eyes to share most computations during the stereo rendering with bit-accurate quality. With minimal hardware augmentations, Nebula achieves 2.7$\times$ motion-to-photon speedup and reduces 1925% bandwidth over lossy video streaming. △ Less

Submitted 23 December, 2025; originally announced December 2025.

Optimistic TEE-Rollups: A Hybrid Architecture for Scalable and Verifiable Generative AI Inference on Blockchain

Authors: Aaron Chan, Alex Ding, Frank Chen, Alan Wu, Bruce Zhang, Arther Tian

Abstract: The rapid integration of Large Language Models (LLMs) into decentralized physical infrastructure networks (DePIN) is currently bottlenecked by the Verifiability Trilemma, which posits that a decentralized inference system cannot simultaneously achieve high computational integrity, low latency, and low cost. Existing cryptographic solutions, such as Zero-Knowledge Machine Learning (ZKML), suffer fr… ▽ More The rapid integration of Large Language Models (LLMs) into decentralized physical infrastructure networks (DePIN) is currently bottlenecked by the Verifiability Trilemma, which posits that a decentralized inference system cannot simultaneously achieve high computational integrity, low latency, and low cost. Existing cryptographic solutions, such as Zero-Knowledge Machine Learning (ZKML), suffer from superlinear proving overheads (O(k NlogN)) that render them infeasible for billionparameter models. Conversely, optimistic approaches (opML) impose prohibitive dispute windows, preventing real-time interactivity, while recent "Proof of Quality" (PoQ) paradigms sacrifice cryptographic integrity for subjective semantic evaluation, leaving networks vulnerable to model downgrade attacks and reward hacking. In this paper, we introduce Optimistic TEE-Rollups (OTR), a hybrid verification protocol that harmonizes these constraints. OTR leverages NVIDIA H100 Confidential Computing Trusted Execution Environments (TEEs) to provide sub-second Provisional Finality, underpinned by an optimistic fraud-proof mechanism and stochastic Zero-Knowledge spot-checks to mitigate hardware side-channel risks. We formally define Proof of Efficient Attribution (PoEA), a consensus mechanism that cryptographically binds execution traces to hardware attestations, thereby guaranteeing model authenticity. Extensive simulations demonstrate that OTR achieves 99% of the throughput of centralized baselines with a marginal cost overhead of $0.07 per query, maintaining Byzantine fault tolerance against rational adversaries even in the presence of transient hardware vulnerabilities. △ Less

Submitted 23 December, 2025; originally announced December 2025.

D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning

Authors: Evelyn Zhang, Fufu Yu, Aoqi Wu, Zichen Wen, Ke Yan, Shouhong Ding, Biqing Qi, Linfeng Zhang

Abstract: Processing long visual token sequences poses a significant computational burden on Multimodal Large Language Models (MLLMs). While token pruning offers a path to acceleration, we find that current methods, while adequate for general understanding, catastrophically fail on fine-grained localization tasks. We attribute this failure to the inherent flaws of the two prevailing strategies: importance-b… ▽ More Processing long visual token sequences poses a significant computational burden on Multimodal Large Language Models (MLLMs). While token pruning offers a path to acceleration, we find that current methods, while adequate for general understanding, catastrophically fail on fine-grained localization tasks. We attribute this failure to the inherent flaws of the two prevailing strategies: importance-based methods suffer from a strong positional bias, an inherent model artifact that distracts from semantic content, while diversity-based methods exhibit structural blindness, disregarding the user's prompt and spatial redundancy. To address this, we introduce D2Pruner, a framework that rectifies these issues by uniquely combining debiased importance with a structural pruning mechanism. Our method first secures a core set of the most critical tokens as pivots based on a debiased attention score. It then performs a Maximal Independent Set (MIS) selection on the remaining tokens, which are modeled on a hybrid graph where edges signify spatial proximity and semantic similarity. This process iteratively preserves the most important and available token while removing its neighbors, ensuring that the supplementary tokens are chosen to maximize importance and diversity. Extensive experiments demonstrate that D2Pruner has exceptional efficiency and fidelity. Applied to LLaVA-1.5-7B for general understanding tasks, it reduces FLOPs by 74.2\% while retaining 99.2\% of its original performance. Furthermore, in challenging localization benchmarks with InternVL-2.5-8B, it maintains 85.7\% performance at a 90\% token reduction rate, marking a significant advancement with up to 63. 53\% improvement over existing methods. △ Less

Submitted 22 December, 2025; originally announced December 2025.

Design and Evaluation of Cost-Aware PoQ for Decentralized LLM Inference

Authors: Arther Tian, Alex Ding, Frank Chen, Alan Wu, Aaron Chan, Bruce Zhang

Abstract: Decentralized large language model (LLM) inference promises transparent and censorship resistant access to advanced AI, yet existing verification approaches struggle to scale to modern models. Proof of Quality (PoQ) replaces cryptographic verification of computation with consensus over output quality, but the original formulation ignores heterogeneous computational costs across inference and evalu… ▽ More Decentralized large language model (LLM) inference promises transparent and censorship resistant access to advanced AI, yet existing verification approaches struggle to scale to modern models. Proof of Quality (PoQ) replaces cryptographic verification of computation with consensus over output quality, but the original formulation ignores heterogeneous computational costs across inference and evaluator nodes. This paper introduces a cost-aware PoQ framework that integrates explicit efficiency measurements into the reward mechanism for both types of nodes. The design combines ground truth token level F1, lightweight learned evaluators, and GPT based judgments within a unified evaluation pipeline, and adopts a linear reward function that balances normalized quality and cost. Experiments on extractive question answering and abstractive summarization use five instruction tuned LLMs ranging from TinyLlama-1.1B to Llama-3.2-3B and three evaluation models spanning cross encoder and bi encoder architectures. Results show that a semantic textual similarity bi encoder achieves much higher correlation with both ground truth and GPT scores than cross encoders, indicating that evaluator architecture is a critical design choice for PoQ. Quality-cost analysis further reveals that the largest models in the pool are also the most efficient in terms of quality per unit latency. Monte Carlo simulations over 5\,000 PoQ rounds demonstrate that the cost-aware reward scheme consistently assigns higher average rewards to high quality low cost inference models and to efficient evaluators, while penalizing slow low quality nodes. These findings suggest that cost-aware PoQ provides a practical foundation for economically sustainable decentralized LLM inference. △ Less

Submitted 18 December, 2025; originally announced December 2025.

FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection

Authors: Ziyu Huang, Yangjie Zhou, Zihan Liu, Xinhao Luo, Yijia Diao, Minyi Guo, Jidong Zhai, Yu Feng, Chen Zhang, Anbang Wu, Jingwen Leng

Abstract: The scaling of computation throughput continues to outpace improvements in memory bandwidth, making many deep learning workloads memory-bound. Kernel fusion is a key technique to alleviate this problem, but the fusion strategies of existing compilers and frameworks are limited to using local scratchpad memory. When the intermediate results exceed the limited capacity (such as FFN), the fusion fail… ▽ More The scaling of computation throughput continues to outpace improvements in memory bandwidth, making many deep learning workloads memory-bound. Kernel fusion is a key technique to alleviate this problem, but the fusion strategies of existing compilers and frameworks are limited to using local scratchpad memory. When the intermediate results exceed the limited capacity (such as FFN), the fusion fails. Although modern GPUs (like the NVIDIA H100) now incorporate an inter-core connection mechanism known as Distributed Shared Memory(DSM)--providing a larger, high-bandwidth, and low-latency on-chip memory pool--this hardware potential has yet to be exploited by software frameworks. To bridge this gap, we present FlashFuser, the first compiler framework to utilize inter-core connection for kernel fusion on modern GPUs. FlashFuser extends established fusion techniques to the DSM domain through three core contributions. First, we propose a powerful DSM-based communication abstraction that formalizes complex cluster-based data exchange patterns, such as reduce, shuffle and multiply. Second, we introduce a dataflow analyzer that generalizes loop scheduling, resource mapping, and tile selection to the distributed memory hierarchy; it determines the optimal execution order and tile sizes by quantifying data movement across memory levels. Finally, FlashFuser integrates these components into a unified search engine that employs analytical cost modeling and DSM-aware pruning strategies to efficiently discover the optimal execution plan. Our evaluation on an NVIDIA H100 GPU shows that FlashFuser reduces memory access by 58% and delivers kernel speedups of 3.3x against highly-tuned libraries and 4.1x against state-of-the-art compilers, resulting in a 1.24x end-to-end speedup. △ Less

Submitted 14 December, 2025; originally announced December 2025.

Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing

Authors: Justin W. Lin, Eliot Krzysztof Jones, Donovan Julian Jasper, Ethan Jun-shen Ho, Anna Wu, Arnold Tianyi Yang, Neil Perry, Andy Zou, Matt Fredrikson, J. Zico Kolter, Percy Liang, Dan Boneh, Daniel E. Ho

Abstract: We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals alongside six existing AI agents and ARTEMIS, our new agent scaffold, on a large university network consisting of ~8,000 hosts across 12 subnets. ARTEMIS is a multi-agent framework featuring dynamic prompt generation, arb… ▽ More We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals alongside six existing AI agents and ARTEMIS, our new agent scaffold, on a large university network consisting of ~8,000 hosts across 12 subnets. ARTEMIS is a multi-agent framework featuring dynamic prompt generation, arbitrary sub-agents, and automatic vulnerability triaging. In our comparative study, ARTEMIS placed second overall, discovering 9 valid vulnerabilities with an 82% valid submission rate and outperforming 9 of 10 human participants. While existing scaffolds such as Codex and CyAgent underperformed relative to most human participants, ARTEMIS demonstrated technical sophistication and submission quality comparable to the strongest participants. We observe that AI agents offer advantages in systematic enumeration, parallel exploitation, and cost -- certain ARTEMIS variants cost $18/hour versus $60/hour for professional penetration testers. We also identify key capability gaps: AI agents exhibit higher false-positive rates and struggle with GUI-based tasks. △ Less

Submitted 10 December, 2025; originally announced December 2025.

Distracted Robot: How Visual Clutter Undermine Robotic Manipulation

Authors: Amir Rasouli, Montgomery Alban, Sajjad Pakdamansavoji, Zhiyuan Li, Zhanguang Zhang, Aaron Wu, Xuan Zhao

Abstract: In this work, we propose an evaluation protocol for examining the performance of robotic manipulation policies in cluttered scenes. Contrary to prior works, we approach evaluation from a psychophysical perspective, therefore we use a unified measure of clutter that accounts for environmental factors as well as the distractors quantity, characteristics, and arrangement. Using this measure, we syste… ▽ More In this work, we propose an evaluation protocol for examining the performance of robotic manipulation policies in cluttered scenes. Contrary to prior works, we approach evaluation from a psychophysical perspective, therefore we use a unified measure of clutter that accounts for environmental factors as well as the distractors quantity, characteristics, and arrangement. Using this measure, we systematically construct evaluation scenarios in both hyper-realistic simulation and real-world and conduct extensive experimentation on manipulation policies, in particular vision-language-action (VLA) models. Our experiments highlight the significant impact of scene clutter, lowering the performance of the policies, by as much as 34% and show that despite achieving similar average performance across the tasks, different VLA policies have unique vulnerabilities and a relatively low agreement on success scenarios. We further show that our clutter measure is an effective indicator of performance degradation and analyze the impact of distractors in terms of their quantity and occluding influence. At the end, we show that finetuning on enhanced data, although effective, does not equally remedy all negative impacts of clutter on performance. △ Less

Submitted 27 November, 2025; originally announced November 2025.

Comments: 12 figures, 2 tables

Robust Detection of Retinal Neovascularization in Widefield Optical Coherence Tomography

Authors: Jinyi Hao, Jie Wang, Kotaro Tsuboi, Liqin Gao, Tristan T. Hormel, Yukun Guo, An-Lun Wu, Min Gao, Christina J. Flaxel, Steven T. Bailey, Thomas S. Hwang, Yali Jia

Abstract: Retinal neovascularization (RNV) is a vision threatening development in diabetic retinopathy (DR). Vision loss associated with RNV is preventable with timely intervention, making RNV clinical screening and monitoring a priority. Optical coherence tomography (OCT) angiography (OCTA) provides high-resolution imaging and high-sensitivity detection of RNV lesions. With recent commercial devices introd… ▽ More Retinal neovascularization (RNV) is a vision threatening development in diabetic retinopathy (DR). Vision loss associated with RNV is preventable with timely intervention, making RNV clinical screening and monitoring a priority. Optical coherence tomography (OCT) angiography (OCTA) provides high-resolution imaging and high-sensitivity detection of RNV lesions. With recent commercial devices introducing widefield OCTA imaging to the clinic, the technology stands to improve early detection of RNV pathology. However, to meet clinical requirements these imaging capabilities must be combined with effective RNV detection and quantification, but existing algorithms for OCTA images are optimized for conventional, i.e. narrow, fields of view. Here, we present a novel approach for RNV diagnosis and staging on widefield OCT/OCTA. Unlike conventional methods dependent on multi-layer retinal segmentation, our model reframes RNV identification as a direct binary localization task. Our fully automated approach was trained and validated on 589 widefield scans (17x17-mm to 26x21-mm) collected from multiple devices at multiple clinics. Our method achieved a device-dependent area under curve (AUC) ranging from 0.96 to 0.99 for RNV diagnosis, and mean intersection over union (IOU) ranging from 0.76 to 0.88 for segmentation. We also demonstrate our method's ability to monitor lesion growth longitudinally. Our results indicate that deep learning-based analysis for widefield OCTA images could offer a valuable means for improving RNV screening and management. △ Less

Submitted 21 November, 2025; originally announced November 2025.

Comments: 17 pages, 11 figures. Submitted to Optica. Corresponding author: Yali Jia. Affiliations: ((1) Casey Eye Institute, Oregon Health & Science University, USA (2) Department of Ophthalmology, Aichi Medical University, Japan (3) Department of Biomedical Engineering, Oregon Health & Science University, USA (4) Department of Ophthalmology, Mackay Memorial Hospital, Taiwan)

Addressing A Posteriori Performance Degradation in Neural Network Subgrid Stress Models

Authors: Andy Wu, Sanjiva K. Lele

Abstract: Neural network subgrid stress models often have a priori performance that is far better than the a posteriori performance, leading to neural network models that look very promising a priori completely failing in a posteriori Large Eddy Simulations (LES). This performance gap can be decreased by combining two different methods, training data augmentation and reducing input complexity to the neural… ▽ More Neural network subgrid stress models often have a priori performance that is far better than the a posteriori performance, leading to neural network models that look very promising a priori completely failing in a posteriori Large Eddy Simulations (LES). This performance gap can be decreased by combining two different methods, training data augmentation and reducing input complexity to the neural network. Augmenting the training data with two different filters before training the neural networks has no performance degradation a priori as compared to a neural network trained with one filter. A posteriori, neural networks trained with two different filters are far more robust across two different LES codes with different numerical schemes. In addition, by ablating away the higher order terms input into the neural network, the a priori versus a posteriori performance changes become less apparent. When combined, neural networks that use both training data augmentation and a less complex set of inputs have a posteriori performance far more reflective of their a priori evaluation. △ Less

Submitted 21 November, 2025; originally announced November 2025.

A Disentangled Low-Rank RNN Framework for Uncovering Neural Connectivity and Dynamics

Authors: Chengrui Li, Yunmiao Wang, Yule Wang, Weihan Li, Dieter Jaeger, Anqi Wu

Abstract: Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity. Although their functional connectivity is low-rank, it lacks disentanglement interpretations, making it difficult to assign distinct computational roles to different latent dimensions. To address this, we propose the Disentangled Recurrent Neural Net… ▽ More Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity. Although their functional connectivity is low-rank, it lacks disentanglement interpretations, making it difficult to assign distinct computational roles to different latent dimensions. To address this, we propose the Disentangled Recurrent Neural Network (DisRNN), a generative lrRNN framework that assumes group-wise independence among latent dynamics while allowing flexible within-group entanglement. These independent latent groups allow latent dynamics to evolve separately, but are internally rich for complex computation. We reformulate the lrRNN under a variational autoencoder (VAE) framework, enabling us to introduce a partial correlation penalty that encourages disentanglement between groups of latent dimensions. Experiments on synthetic, monkey M1, and mouse voltage imaging data show that DisRNN consistently improves the disentanglement and interpretability of learned neural latent trajectories in low-dimensional space and low-rank connectivity over baseline lrRNNs that do not encourage partial disentanglement. △ Less

Submitted 17 November, 2025; originally announced November 2025.

Simulating Distribution Dynamics: Liquid Temporal Feature Evolution for Single-Domain Generalized Object Detection

Authors: Zihao Zhang, Yang Li, Aming Wu, Yahong Han

Abstract: In this paper, we focus on Single-Domain Generalized Object Detection (Single-DGOD), aiming to transfer a detector trained on one source domain to multiple unknown domains. Existing methods for Single-DGOD typically rely on discrete data augmentation or static perturbation methods to expand data diversity, thereby mitigating the lack of access to target domain data. However, in real-world scenario… ▽ More In this paper, we focus on Single-Domain Generalized Object Detection (Single-DGOD), aiming to transfer a detector trained on one source domain to multiple unknown domains. Existing methods for Single-DGOD typically rely on discrete data augmentation or static perturbation methods to expand data diversity, thereby mitigating the lack of access to target domain data. However, in real-world scenarios such as changes in weather or lighting conditions, domain shifts often occur continuously and gradually. Discrete augmentations and static perturbations fail to effectively capture the dynamic variation of feature distributions, thereby limiting the model's ability to perceive fine-grained cross-domain differences. To this end, we propose a new method, Liquid Temporal Feature Evolution, which simulates the progressive evolution of features from the source domain to simulated latent distributions by incorporating temporal modeling and liquid neural network-driven parameter adjustment. Specifically, we introduce controllable Gaussian noise injection and multi-scale Gaussian blurring to simulate initial feature perturbations, followed by temporal modeling and a liquid parameter adjustment mechanism to generate adaptive modulation parameters, enabling a smooth and continuous adaptation across domains. By capturing progressive cross-domain feature evolution and dynamically regulating adaptation paths, our method bridges the source-unknown domain distribution gap, significantly boosting generalization and robustness to unseen shifts. Significant performance improvements on the Diverse Weather dataset and Real-to-Art benchmark demonstrate the superiority of our method. Our code is available at https://github.com/2490o/LTFE. △ Less

Submitted 12 November, 2025; originally announced November 2025.

Mamba-driven multi-perspective structural understanding for molecular ground-state conformation prediction

Authors: Yuxin Gou, Aming Wu, Richang Hong, Meng Wang

Abstract: A comprehensive understanding of molecular structures is important for the prediction of molecular ground-state conformation involving property information. Meanwhile, state space model (e.g., Mamba) has recently emerged as a promising mechanism for long sequence modeling and has achieved remarkable results in various language and vision tasks. However, towards molecular ground-state conformation… ▽ More A comprehensive understanding of molecular structures is important for the prediction of molecular ground-state conformation involving property information. Meanwhile, state space model (e.g., Mamba) has recently emerged as a promising mechanism for long sequence modeling and has achieved remarkable results in various language and vision tasks. However, towards molecular ground-state conformation prediction, exploiting Mamba to understand molecular structure is underexplored. To this end, we strive to design a generic and efficient framework with Mamba to capture critical components. In general, molecular structure could be considered to consist of three elements, i.e., atom types, atom positions, and connections between atoms. Thus, considering the three elements, an approach of Mamba-driven multi-perspective structural understanding (MPSU-Mamba) is proposed to localize molecular ground-state conformation. Particularly, for complex and diverse molecules, three different kinds of dedicated scanning strategies are explored to construct a comprehensive perception of corresponding molecular structures. And a bright-channel guided mechanism is defined to discriminate the critical conformation-related atom information. Experimental results on QM9 and Molecule3D datasets indicate that MPSU-Mamba significantly outperforms existing methods. Furthermore, we observe that for the case of few training samples, MPSU-Mamba still achieves superior performance, demonstrating that our method is indeed beneficial for understanding molecular structures. △ Less

Submitted 10 November, 2025; originally announced November 2025.

Large Language Models Develop Novel Social Biases Through Adaptive Exploration

Authors: Addison J. Wu, Ryan Liu, Xuechunzi Bai, Thomas L. Griffiths

Abstract: As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important to ensure that they are unbiased. In this paper, we argue that the predominant approach of simply removing existing biases from models is not enough. Using a paradigm from the psychology literature, we demonstrate that LLMs can spontaneously develop novel so… ▽ More As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important to ensure that they are unbiased. In this paper, we argue that the predominant approach of simply removing existing biases from models is not enough. Using a paradigm from the psychology literature, we demonstrate that LLMs can spontaneously develop novel social biases about artificial demographic groups even when no inherent differences exist. These biases result in highly stratified task allocations, which are less fair than assignments by human participants and are exacerbated by newer and larger models. In social science, emergent biases like these have been shown to result from exploration-exploitation trade-offs, where the decision-maker explores too little, allowing early observations to strongly influence impressions about entire demographic groups. To alleviate this effect, we examine a series of interventions targeting model inputs, problem structure, and explicit steering. We find that explicitly incentivizing exploration most robustly reduces stratification, highlighting the need for better multifaceted objectives to mitigate bias. These results reveal that LLMs are not merely passive mirrors of human social biases, but can actively create new ones from experience, raising urgent questions about how these systems will shape societies over time. △ Less

Submitted 22 December, 2025; v1 submitted 8 November, 2025; originally announced November 2025.

MoME: Mixture of Visual Language Medical Experts for Medical Imaging Segmentation

Authors: Arghavan Rezvani, Xiangyi Yan, Anthony T. Wu, Kun Han, Pooya Khosravi, Xiaohui Xie

Abstract: In this study, we propose MoME, a Mixture of Visual Language Medical Experts, for Medical Image Segmentation. MoME adapts the successful Mixture of Experts (MoE) paradigm, widely used in Large Language Models (LLMs), for medical vision-language tasks. The architecture enables dynamic expert selection by effectively utilizing multi-scale visual features tailored to the intricacies of medical imager… ▽ More In this study, we propose MoME, a Mixture of Visual Language Medical Experts, for Medical Image Segmentation. MoME adapts the successful Mixture of Experts (MoE) paradigm, widely used in Large Language Models (LLMs), for medical vision-language tasks. The architecture enables dynamic expert selection by effectively utilizing multi-scale visual features tailored to the intricacies of medical imagery, enriched with textual embeddings. This work explores a novel integration of vision-language models for this domain. Utilizing an assembly of 10 datasets, encompassing 3,410 CT scans, MoME demonstrates strong performance on a comprehensive medical imaging segmentation benchmark. Our approach explores the integration of foundation models for medical imaging, benefiting from the established efficacy of MoE in boosting model performance by incorporating textual information. Demonstrating competitive precision across multiple datasets, MoME explores a novel architecture for achieving robust results in medical image analysis. △ Less

Submitted 30 October, 2025; originally announced October 2025.

DiSE: A diffusion probabilistic model for automatic structure elucidation of organic compounds

Authors: Haochen Chen, Qi Huang, Anan Wu, Wenhao Zhang, Jianliang Ye, Jianming Wu, Kai Tan, Xin Lu, Xin Xu

Abstract: Automatic structure elucidation is essential for self-driving laboratories as it enables the system to achieve truly autonomous. This capability closes the experimental feedback loop, ensuring that machine learning models receive reliable structure information for real-time decision-making and optimization. Herein, we present DiSE, an end-to-end diffusion-based generative model that integrates mul… ▽ More Automatic structure elucidation is essential for self-driving laboratories as it enables the system to achieve truly autonomous. This capability closes the experimental feedback loop, ensuring that machine learning models receive reliable structure information for real-time decision-making and optimization. Herein, we present DiSE, an end-to-end diffusion-based generative model that integrates multiple spectroscopic modalities, including MS, 13C and 1H chemical shifts, HSQC, and COSY, to achieve automated yet accurate structure elucidation of organic compounds. By learning inherent correlations among spectra through data-driven approaches, DiSE achieves superior accuracy, strong generalization across chemically diverse datasets, and robustness to experimental data despite being trained on calculated spectra. DiSE thus represents a significant advance toward fully automated structure elucidation, with broad potential in natural product research, drug discovery, and self-driving laboratories. △ Less

Submitted 30 October, 2025; originally announced October 2025.

OracleAgent: A Multimodal Reasoning Agent for Oracle Bone Script Research

Authors: Caoshuo Li, Zengmao Ding, Xiaobin Hu, Bang Li, Donghao Luo, Xu Peng, Taisong Jin, Yongge Liu, Shengwei Han, Jing Yang, Xiaoping He, Feng Gao, AndyPian Wu, SevenShu, Chaoyang Wang, Chengjie Wang

Abstract: As one of the earliest writing systems, Oracle Bone Script (OBS) preserves the cultural and intellectual heritage of ancient civilizations. However, current OBS research faces two major challenges: (1) the interpretation of OBS involves a complex workflow comprising multiple serial and parallel sub-tasks, and (2) the efficiency of OBS information organization and retrieval remains a critical bottl… ▽ More As one of the earliest writing systems, Oracle Bone Script (OBS) preserves the cultural and intellectual heritage of ancient civilizations. However, current OBS research faces two major challenges: (1) the interpretation of OBS involves a complex workflow comprising multiple serial and parallel sub-tasks, and (2) the efficiency of OBS information organization and retrieval remains a critical bottleneck, as scholars often spend substantial effort searching for, compiling, and managing relevant resources. To address these challenges, we present OracleAgent, the first agent system designed for the structured management and retrieval of OBS-related information. OracleAgent seamlessly integrates multiple OBS analysis tools, empowered by large language models (LLMs), and can flexibly orchestrate these components. Additionally, we construct a comprehensive domain-specific multimodal knowledge base for OBS, which is built through a rigorous multi-year process of data collection, cleaning, and expert annotation. The knowledge base comprises over 1.4M single-character rubbing images and 80K interpretation texts. OracleAgent leverages this resource through its multimodal tools to assist experts in retrieval tasks of character, document, interpretation text, and rubbing image. Extensive experiments demonstrate that OracleAgent achieves superior performance across a range of multimodal reasoning and generation tasks, surpassing leading mainstream multimodal large language models (MLLMs) (e.g., GPT-4o). Furthermore, our case study illustrates that OracleAgent can effectively assist domain experts, significantly reducing the time cost of OBS research. These results highlight OracleAgent as a significant step toward the practical deployment of OBS-assisted research and automated interpretation systems. △ Less

Submitted 29 October, 2025; originally announced October 2025.

Enhancing Vision-Language Models for Autonomous Driving through Task-Specific Prompting and Spatial Reasoning

Authors: Aodi Wu, Xubo Luo

Abstract: This technical report presents our solution for the RoboSense Challenge at IROS 2025, which evaluates Vision-Language Models (VLMs) on autonomous driving scene understanding across perception, prediction, planning, and corruption detection tasks. We propose a systematic framework built on four core components. First, a Mixture-of-Prompts router classifies questions and dispatches them to task-spec… ▽ More This technical report presents our solution for the RoboSense Challenge at IROS 2025, which evaluates Vision-Language Models (VLMs) on autonomous driving scene understanding across perception, prediction, planning, and corruption detection tasks. We propose a systematic framework built on four core components. First, a Mixture-of-Prompts router classifies questions and dispatches them to task-specific expert prompts, eliminating interference across diverse question types. Second, task-specific prompts embed explicit coordinate systems, spatial reasoning rules, role-playing, Chain-of-Thought/Tree-of-Thought reasoning, and few-shot examples tailored to each task. Third, a visual assembly module composes multi-view images with object crops, magenta markers, and adaptive historical frames based on question requirements. Fourth, we configure model inference parameters (temperature, top-p, message roles) per task to optimize output quality. Implemented on Qwen2.5-VL-72B, our approach achieves 70.87% average accuracy on Phase-1 (clean data) and 72.85% on Phase-2 (corrupted data), demonstrating that structured prompting and spatial grounding substantially enhance VLM performance on safety-critical autonomous driving tasks. Code and prompt are available at https://github.com/wuaodi/UCAS-CSU-phase2. △ Less

Submitted 28 October, 2025; originally announced October 2025.

Comments: RoboSense Challenge with IROS 2025

Are Large Language Models Sensitive to the Motives Behind Communication?

Authors: Addison J. Wu, Ryan Liu, Kerem Oktar, Theodore R. Sumers, Thomas L. Griffiths

Abstract: Human communication is motivated: people speak, write, and create content with a particular communicative intent in mind. As a result, information that large language models (LLMs) and AI agents process is inherently framed by humans' intentions and incentives. People are adept at navigating such nuanced information: we routinely identify benevolent or self-serving motives in order to decide what… ▽ More Human communication is motivated: people speak, write, and create content with a particular communicative intent in mind. As a result, information that large language models (LLMs) and AI agents process is inherently framed by humans' intentions and incentives. People are adept at navigating such nuanced information: we routinely identify benevolent or self-serving motives in order to decide what statements to trust. For LLMs to be effective in the real world, they too must critically evaluate content by factoring in the motivations of the source -- for instance, weighing the credibility of claims made in a sales pitch. In this paper, we undertake a comprehensive study of whether LLMs have this capacity for motivational vigilance. We first employ controlled experiments from cognitive science to verify that LLMs' behavior is consistent with rational models of learning from motivated testimony, and find they successfully discount information from biased sources in a human-like manner. We then extend our evaluation to sponsored online adverts, a more naturalistic reflection of LLM agents' information ecosystems. In these settings, we find that LLMs' inferences do not track the rational models' predictions nearly as closely -- partly due to additional information that distracts them from vigilance-relevant considerations. However, a simple steering intervention that boosts the salience of intentions and incentives substantially increases the correspondence between LLMs and the rational model. These results suggest that LLMs possess a basic sensitivity to the motivations of others, but generalizing to novel real-world settings will require further improvements to these models. △ Less

Submitted 22 October, 2025; originally announced October 2025.

Comments: NeurIPS 2025

Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning

Authors: Yang Li, Aming Wu, Zihao Zhang, Yahong Han

Abstract: In this paper, we focus on Novel Class Discovery for Point Cloud Segmentation (3D-NCD), aiming to learn a model that can segment unlabeled (novel) 3D classes using only the supervision from labeled (base) 3D classes. The key to this task is to setup the exact correlations between the point representations and their base class labels, as well as the representation correlations between the points fr… ▽ More In this paper, we focus on Novel Class Discovery for Point Cloud Segmentation (3D-NCD), aiming to learn a model that can segment unlabeled (novel) 3D classes using only the supervision from labeled (base) 3D classes. The key to this task is to setup the exact correlations between the point representations and their base class labels, as well as the representation correlations between the points from base and novel classes. A coarse or statistical correlation learning may lead to the confusion in novel class inference. lf we impose a causal relationship as a strong correlated constraint upon the learning process, the essential point cloud representations that accurately correspond to the classes should be uncovered. To this end, we introduce a structural causal model (SCM) to re-formalize the 3D-NCD problem and propose a new method, i.e., Joint Learning of Causal Representation and Reasoning. Specifically, we first analyze hidden confounders in the base class representations and the causal relationships between the base and novel classes through SCM. We devise a causal representation prototype that eliminates confounders to capture the causal representations of base classes. A graph structure is then used to model the causal relationships between the base classes' causal representation prototypes and the novel class prototypes, enabling causal reasoning from base to novel classes. Extensive experiments and visualization results on 3D and 2D NCD semantic segmentation demonstrate the superiorities of our method. △ Less

Submitted 22 October, 2025; v1 submitted 15 October, 2025; originally announced October 2025.

Comments: Accepted by NeurIPS 2025

Constant in an Ever-Changing World

Authors: Andy Wu, Chun-Cheng Lin, Yuehua Huang, Rung-Tzuo Liaw

Abstract: The training process of reinforcement learning often suffers from severe oscillations, leading to instability and degraded performance. In this paper, we propose a Constant in an Ever-Changing World (CIC) framework that enhances algorithmic stability to improve performance. CIC maintains both a representative policy and a current policy. Instead of updating the representative policy blindly, CIC s… ▽ More The training process of reinforcement learning often suffers from severe oscillations, leading to instability and degraded performance. In this paper, we propose a Constant in an Ever-Changing World (CIC) framework that enhances algorithmic stability to improve performance. CIC maintains both a representative policy and a current policy. Instead of updating the representative policy blindly, CIC selectively updates it only when the current policy demonstrates superiority. Furthermore, CIC employs an adaptive adjustment mechanism, enabling the representative and current policies to jointly facilitate critic training. We evaluate CIC on five MuJoCo environments, and the results show that CIC improves the performance of conventional algorithms without incurring additional computational cost. △ Less

Submitted 1 October, 2025; originally announced October 2025.

Comments: in Chinese language

Distributional Inverse Reinforcement Learning

Authors: Feiyang Wu, Ye Zhao, Anqi Wu

Abstract: We propose a distributional framework for offline Inverse Reinforcement Learning (IRL) that jointly models uncertainty over reward functions and full distributions of returns. Unlike conventional IRL approaches that recover a deterministic reward estimate or match only expected returns, our method captures richer structure in expert behavior, particularly in learning the reward distribution, by mi… ▽ More We propose a distributional framework for offline Inverse Reinforcement Learning (IRL) that jointly models uncertainty over reward functions and full distributions of returns. Unlike conventional IRL approaches that recover a deterministic reward estimate or match only expected returns, our method captures richer structure in expert behavior, particularly in learning the reward distribution, by minimizing first-order stochastic dominance (FSD) violations and thus integrating distortion risk measures (DRMs) into policy learning, enabling the recovery of both reward distributions and distribution-aware policies. This formulation is well-suited for behavior analysis and risk-aware imitation learning. Empirical results on synthetic benchmarks, real-world neurobehavioral data, and MuJoCo control tasks demonstrate that our method recovers expressive reward representations and achieves state-of-the-art imitation performance. △ Less

Submitted 6 October, 2025; v1 submitted 3 October, 2025; originally announced October 2025.

Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided Diffusion

Authors: Yule Wang, Joseph Yu, Chengrui Li, Weihan Li, Anqi Wu

Abstract: Understanding how neural populations in higher visual areas encode object-centered visual information remains a central challenge in computational neuroscience. Prior works have investigated representational alignment between artificial neural networks and the visual cortex. Nevertheless, these findings are indirect and offer limited insights to the structure of neural populations themselves. Simi… ▽ More Understanding how neural populations in higher visual areas encode object-centered visual information remains a central challenge in computational neuroscience. Prior works have investigated representational alignment between artificial neural networks and the visual cortex. Nevertheless, these findings are indirect and offer limited insights to the structure of neural populations themselves. Similarly, decoding-based methods have quantified semantic features from neural populations but have not uncovered their underlying organizations. This leaves open a scientific question: "how feature-specific visual information is distributed across neural populations in higher visual areas, and whether it is organized into structured, semantically meaningful subspaces." To tackle this problem, we present MIG-Vis, a method that leverages the generative power of diffusion models to visualize and validate the visual-semantic attributes encoded in neural latent subspaces. Our method first uses a variational autoencoder to infer a group-wise disentangled neural latent subspace from neural populations. Subsequently, we propose a mutual information (MI)-guided diffusion synthesis procedure to visualize the specific visual-semantic features encoded by each latent group. We validate MIG-Vis on multi-session neural spiking datasets from the inferior temporal (IT) cortex of two macaques. The synthesized results demonstrate that our method identifies neural latent groups with clear semantic selectivity to diverse visual features, including object pose, inter-category transformations, and intra-class content. These findings provide direct, interpretable evidence of structured semantic representation in the higher visual cortex and advance our understanding of its encoding principles. △ Less

Submitted 2 October, 2025; originally announced October 2025.

Multi-Actor Multi-Critic Deep Deterministic Reinforcement Learning with a Novel Q-Ensemble Method

Authors: Andy Wu, Chun-Cheng Lin, Rung-Tzuo Liaw, Yuehua Huang, Chihjung Kuo, Chia Tong Weng

Abstract: Reinforcement learning has gathered much attention in recent years due to its rapid development and rich applications, especially on control systems and robotics. When tackling real-world applications with reinforcement learning method, the corresponded Markov decision process may have huge discrete or even continuous state/action space. Deep reinforcement learning has been studied for handling th… ▽ More Reinforcement learning has gathered much attention in recent years due to its rapid development and rich applications, especially on control systems and robotics. When tackling real-world applications with reinforcement learning method, the corresponded Markov decision process may have huge discrete or even continuous state/action space. Deep reinforcement learning has been studied for handling these issues through deep learning for years, and one promising branch is the actor-critic architecture. Many past studies leveraged multiple critics to enhance the accuracy of evaluation of a policy for addressing the overestimation and underestimation issues. However, few studies have considered the architecture with multiple actors together with multiple critics. This study proposes a novel multi-actor multi-critic (MAMC) deep deterministic reinforcement learning method. The proposed method has three main features, including selection of actors based on non-dominated sorting for exploration with respect to skill and creativity factors, evaluation for actors and critics using a quantile-based ensemble strategy, and exploiting actors with best skill factor. Theoretical analysis proves the learning stability and bounded estimation bias for the MAMC. The present study examines the performance on a well-known reinforcement learning benchmark MuJoCo. Experimental results show that the proposed framework outperforms state-of-the-art deep deterministic based reinforcement learning methods. Experimental analysis also indicates the proposed components are effective. Empirical analysis further investigates the validity of the proposed method, and shows its benefit on complicated problems. The source code can be found at https://github.com/AndyWu101/MAMC. △ Less

Submitted 1 October, 2025; originally announced October 2025.

Hierarchical Diffusion Motion Planning with Task-Conditioned Uncertainty-Aware Priors

Authors: Amelie Minji Kim, Anqi Wu, Ye Zhao

Abstract: We propose a novel hierarchical diffusion planner that embeds task and motion structure directly in the noise model. Unlike standard diffusion-based planners that use zero-mean, isotropic Gaussian noise, we employ a family of task-conditioned structured Gaussians whose means and covariances are derived from Gaussian Process Motion Planning (GPMP): sparse, task-centric key states or their associate… ▽ More We propose a novel hierarchical diffusion planner that embeds task and motion structure directly in the noise model. Unlike standard diffusion-based planners that use zero-mean, isotropic Gaussian noise, we employ a family of task-conditioned structured Gaussians whose means and covariances are derived from Gaussian Process Motion Planning (GPMP): sparse, task-centric key states or their associated timings (or both) are treated as noisy observations to produce a prior instance. We first generalize the standard diffusion process to biased, non-isotropic corruption with closed-form forward and posterior expressions. Building on this, our hierarchy separates prior instantiation from trajectory denoising: the upper level instantiates a task-conditioned structured Gaussian (mean and covariance), and the lower level denoises the full trajectory under that fixed prior. Experiments on Maze2D goal-reaching and KUKA block stacking show improved success rates, smoother trajectories, and stronger task alignment compared to isotropic baselines. Ablation studies indicate that explicitly structuring the corruption process offers benefits beyond simply conditioning the neural network. Overall, our method concentrates probability mass of prior near feasible, smooth, and semantically meaningful trajectories while maintaining tractability. Our project page is available at https://hta-diffusion.github.io. △ Less

Submitted 29 September, 2025; originally announced September 2025.

The-Bodega: A Matlab Toolbox for Biologically Dynamic Microbubble Simulations on Realistic Hemodynamic Microvascular Graphs

Authors: Stephen Alexander Lee, Alexis Leconte, Alice Wu, Jonathan Poree, Maxence Laplante-Berthier, Simon Desrocher, Pierre-Olivier Bouchard, Joshua Kinugasa, Samuel Mihelic, Andreas Linninger, Jean Provost

Abstract: The-Bodega is a Matlab-based toolbox for simulating ground-truth datasets for Ultrasound Localization Microscopy (ULM)-a super resolution imaging technique that resolves microvessels by systematically tracking microbubbles flowing through the microvasculature. The-Bodega enables open-source simulation of stochastic microbubble dynamics through anatomically complex vascular graphs and features a qu… ▽ More The-Bodega is a Matlab-based toolbox for simulating ground-truth datasets for Ultrasound Localization Microscopy (ULM)-a super resolution imaging technique that resolves microvessels by systematically tracking microbubbles flowing through the microvasculature. The-Bodega enables open-source simulation of stochastic microbubble dynamics through anatomically complex vascular graphs and features a quasi-automated pipeline for generating ground-truth ultrasound data from simple vascular inputs. It incorporates sequential Monte Carlo simulations augmented with Poiseuille flow distributions and dynamic pulsatile flow. A key novelty of our framework is its flexibility to accommodate arbitrary vascular architectures and benchmark common ULM algorithms, such as Fourier Ring Correlation and Singular Value Decomposition (SVD) spatiotemporal filtering, on realistic hemodynamic digital phantoms. The-Bodega supports consistent microbubble-to-ultrasound simulations across domains ranging from mouse brains to human hearts and automatically leverages available CPU/GPU parallelization to improve computational efficiency. We demonstrate its versatility in applications including image quality assessment, motion artifact analysis, and the simulation of novel ULM modalities, such as capillary imaging, myocardial reconstruction under beating heart motion, and simulating neurovascular evoked responses. △ Less

Submitted 9 September, 2025; originally announced September 2025.

Comments: 36 Pages, 12 Figures

XOCT: Enhancing OCT to OCTA Translation via Cross-Dimensional Supervised Multi-Scale Feature Learning

Authors: Pooya Khosravi, Kun Han, Anthony T. Wu, Arghavan Rezvani, Zexin Feng, Xiaohui Xie

Abstract: Optical Coherence Tomography Angiography (OCTA) and its derived en-face projections provide high-resolution visualization of the retinal and choroidal vasculature, which is critical for the rapid and accurate diagnosis of retinal diseases. However, acquiring high-quality OCTA images is challenging due to motion sensitivity and the high costs associated with software modifications for conventional… ▽ More Optical Coherence Tomography Angiography (OCTA) and its derived en-face projections provide high-resolution visualization of the retinal and choroidal vasculature, which is critical for the rapid and accurate diagnosis of retinal diseases. However, acquiring high-quality OCTA images is challenging due to motion sensitivity and the high costs associated with software modifications for conventional OCT devices. Moreover, current deep learning methods for OCT-to-OCTA translation often overlook the vascular differences across retinal layers and struggle to reconstruct the intricate, dense vascular details necessary for reliable diagnosis. To overcome these limitations, we propose XOCT, a novel deep learning framework that integrates Cross-Dimensional Supervision (CDS) with a Multi-Scale Feature Fusion (MSFF) network for layer-aware vascular reconstruction. Our CDS module leverages 2D layer-wise en-face projections, generated via segmentation-weighted z-axis averaging, as supervisory signals to compel the network to learn distinct representations for each retinal layer through fine-grained, targeted guidance. Meanwhile, the MSFF module enhances vessel delineation through multi-scale feature extraction combined with a channel reweighting strategy, effectively capturing vascular details at multiple spatial scales. Our experiments on the OCTA-500 dataset demonstrate XOCT's improvements, especially for the en-face projections which are significant for clinical evaluation of retinal pathologies, underscoring its potential to enhance OCTA accessibility, reliability, and diagnostic value for ophthalmic disease detection and monitoring. The code is available at https://github.com/uci-cbcl/XOCT. △ Less

Submitted 9 September, 2025; originally announced September 2025.

Comments: 11 pages, 3 figures, Accepted to MICCAI 2025

ACM Class: J.3

MolmoAct: Action Reasoning Models that can Reason in Space

Authors: Jason Lee, Jiafei Duan, Haoquan Fang, Yuquan Deng, Shuo Liu, Boyang Li, Bohan Fang, Jieyu Zhang, Yi Ru Wang, Sangho Lee, Winson Han, Wilbert Pumacay, Angelica Wu, Rose Hendrix, Karen Farley, Eli VanderBilt, Ali Farhadi, Dieter Fox, Ranjay Krishna

Abstract: Reasoning is central to purposeful action, yet most robotic foundation models map perception and instructions directly to control, which limits adaptability, generalization, and semantic grounding. We introduce Action Reasoning Models (ARMs), a class of robotic foundation models that integrate perception, planning, and control through a structured three-stage pipeline. Our model, MolmoAct, encodes… ▽ More Reasoning is central to purposeful action, yet most robotic foundation models map perception and instructions directly to control, which limits adaptability, generalization, and semantic grounding. We introduce Action Reasoning Models (ARMs), a class of robotic foundation models that integrate perception, planning, and control through a structured three-stage pipeline. Our model, MolmoAct, encodes observations and instructions into depth-aware perception tokens, generates mid-level spatial plans as editable trajectory traces, and predicts precise low-level actions, enabling explainable and steerable behavior. MolmoAct-7B-D achieves strong performance across simulation and real-world settings: 70.5% zero-shot accuracy on SimplerEnv Visual Matching tasks, surpassing closed-source Pi-0 and GR00T N1.5; 86.6% average success on LIBERO, including an additional 6.3% gain over ThinkAct on long-horizon tasks; and in real-world fine-tuning, an additional 10% (single-arm) and an additional 22.7% (bimanual) task progression over Pi-0-FAST. It also outperforms baselines by an additional 23.3% on out-of-distribution generalization and achieves top human-preference scores for open-ended instruction following and trajectory steering. Furthermore, we release, for the first time, the MolmoAct Dataset -- a mid-training robot dataset comprising over 10,000 high quality robot trajectories across diverse scenarios and tasks. Training with this dataset yields an average 5.5% improvement in general performance over the base model. We release all model weights, training code, our collected dataset, and our action reasoning dataset, establishing MolmoAct as both a state-of-the-art robotics foundation model and an open blueprint for building ARMs that transform perception into purposeful action through structured reasoning. Blogpost: https://allenai.org/blog/molmoact △ Less

Submitted 18 September, 2025; v1 submitted 11 August, 2025; originally announced August 2025.

Comments: Updated GR00T result to N1.5

RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions

Authors: Anran Wu, Long Peng, Xin Di, Xueyuan Dai, Chen Wu, Yang Wang, Xueyang Fu, Yang Cao, Zheng-Jun Zha

Abstract: Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically assume that input multi-view images are clean and high-quality. In real-world scenarios, images are often captured under challenging conditions such as noise, lo… ▽ More Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically assume that input multi-view images are clean and high-quality. In real-world scenarios, images are often captured under challenging conditions such as noise, low light, or rain, resulting in inaccurate geometry and degraded 3D reconstruction. To address these challenges, we propose a general and efficient multi-view feature enhancement module, RobustGS, which substantially improves the robustness of feedforward 3DGS methods under various adverse imaging conditions, enabling high-quality 3D reconstruction. The RobustGS module can be seamlessly integrated into existing pretrained pipelines in a plug-and-play manner to enhance reconstruction robustness. Specifically, we introduce a novel component, Generalized Degradation Learner, designed to extract generic representations and distributions of multiple degradations from multi-view inputs, thereby enhancing degradation-awareness and improving the overall quality of 3D reconstruction. In addition, we propose a novel semantic-aware state-space model. It first leverages the extracted degradation representations to enhance corrupted inputs in the feature space. Then, it employs a semantic-aware strategy to aggregate semantically similar information across different views, enabling the extraction of fine-grained cross-view correspondences and further improving the quality of 3D representations. Extensive experiments demonstrate that our approach, when integrated into existing methods in a plug-and-play manner, consistently achieves state-of-the-art reconstruction quality across various types of degradations. △ Less

Submitted 5 August, 2025; originally announced August 2025.

Should Bias Always be Eliminated? A Principled Framework to Use Data Bias for OOD Generation

Authors: Yan Li, Guangyi Chen, Yunlong Deng, Zijian Li, Zeyu Tang, Anpeng Wu, Kun Zhang

Abstract: Most existing methods for adapting models to out-of-distribution (OOD) domains rely on invariant representation learning to eliminate the influence of biased features. However, should bias always be eliminated -- and if not, when should it be retained, and how can it be leveraged? To address these questions, we first present a theoretical analysis that explores the conditions under which biased fe… ▽ More Most existing methods for adapting models to out-of-distribution (OOD) domains rely on invariant representation learning to eliminate the influence of biased features. However, should bias always be eliminated -- and if not, when should it be retained, and how can it be leveraged? To address these questions, we first present a theoretical analysis that explores the conditions under which biased features can be identified and effectively utilized. Building on this theoretical foundation, we introduce a novel framework that strategically leverages bias to complement invariant representations during inference. The framework comprises two key components that leverage bias in both direct and indirect ways: (1) using invariance as guidance to extract predictive ingredients from bias, and (2) exploiting identified bias to estimate the environmental condition and then use it to explore appropriate bias-aware predictors to alleviate environment gaps. We validate our approach through experiments on both synthetic datasets and standard domain generalization benchmarks. Results consistently demonstrate that our method outperforms existing approaches, underscoring its robustness and adaptability. △ Less

Submitted 22 July, 2025; originally announced July 2025.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Authors: Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu , et al. (3410 additional authors not shown)

Abstract: In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal unde… ▽ More In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving. △ Less

Submitted 19 December, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: 72 pages, 17 figures

ReTimeCausal: EM-Augmented Additive Noise Models for Interpretable Causal Discovery in Irregular Time Series

Authors: Weihong Li, Anpeng Wu, Kun Kuang, Keting Yin

Abstract: This paper studies causal discovery in irregularly sampled time series-a pivotal challenge in high-stakes domains like finance, healthcare, and climate science, where missing data and inconsistent sampling frequencies distort causal mechanisms. Traditional methods (e.g., Granger causality, PCMCI) fail to reconcile multi-scale interactions (e.g., hourly storms vs. decadal climate shifts), while neu… ▽ More This paper studies causal discovery in irregularly sampled time series-a pivotal challenge in high-stakes domains like finance, healthcare, and climate science, where missing data and inconsistent sampling frequencies distort causal mechanisms. Traditional methods (e.g., Granger causality, PCMCI) fail to reconcile multi-scale interactions (e.g., hourly storms vs. decadal climate shifts), while neural approaches (e.g., CUTS+) lack interpretability, stemming from a critical gap: existing frameworks either rigidly assume temporal regularity or aggregate dynamics into opaque representations, neglecting real-world granularity and auditable logic. To bridge this gap, we propose ReTimeCausal, a novel integration of Additive Noise Models (ANM) and Expectation-Maximization (EM) that unifies physics-guided data imputation with sparse causal inference. Through kernelized sparse regression and structural constraints, ReTimeCausal iteratively refines missing values (E-step) and causal graphs (M-step), resolving cross-frequency dependencies and missing data issues. Extensive experiments on synthetic and real-world datasets demonstrate that ReTimeCausal outperforms existing state-of-the-art methods under challenging irregular sampling and missing data conditions. △ Less

Submitted 4 July, 2025; originally announced July 2025.

Comments: 12 pages, 2 figures

Rethinking Broken Object Level Authorization Attacks Under Zero Trust Principle

Authors: Anbin Wu, Zhiyong Feng, Ruitao Feng, Zhenchang Xing, Yang Liu

Abstract: RESTful APIs facilitate data exchange between applications, but they also expose sensitive resources to potential exploitation. Broken Object Level Authorization (BOLA) is the top vulnerability in the OWASP API Security Top 10, exemplifies a critical access control flaw where attackers manipulate API parameters to gain unauthorized access. To address this, we propose BOLAZ, a defense framework gro… ▽ More RESTful APIs facilitate data exchange between applications, but they also expose sensitive resources to potential exploitation. Broken Object Level Authorization (BOLA) is the top vulnerability in the OWASP API Security Top 10, exemplifies a critical access control flaw where attackers manipulate API parameters to gain unauthorized access. To address this, we propose BOLAZ, a defense framework grounded in zero trust principles. BOLAZ analyzes the data flow of resource IDs, pinpointing BOLA attack injection points and determining the associated authorization intervals to prevent horizontal privilege escalation. Our approach leverages static taint tracking to categorize APIs into producers and consumers based on how they handle resource IDs. By mapping the propagation paths of resource IDs, BOLAZ captures the context in which these IDs are produced and consumed, allowing for precise identification of authorization boundaries. Unlike defense methods based on common authorization models, BOLAZ is the first authorization-guided method that adapts defense rules based on the system's best-practice authorization logic. We validate BOLAZ through empirical research on 10 GitHub projects. The results demonstrate BOLAZ's effectiveness in defending against vulnerabilities collected from CVE and discovering 35 new BOLA vulnerabilities in the wild, demonstrating its practicality in real-world deployments. △ Less

Submitted 14 July, 2025; v1 submitted 3 July, 2025; originally announced July 2025.

Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios

Authors: Deng Li, Aming Wu, Yang Li, Yaowei Wang, Yahong Han

Abstract: In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual test-time adaptation has attracted much attention, aiming to improve detectors' generalization by fine-tuning a few specific parameters, e.g., BatchNorm layers.… ▽ More In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual test-time adaptation has attracted much attention, aiming to improve detectors' generalization by fine-tuning a few specific parameters, e.g., BatchNorm layers. However, based on a small number of test images, fine-tuning certain parameters may affect the representation ability of other fixed parameters, leading to performance degradation. Instead, we explore a new mechanism, i.e., converting the fine-tuning process to a specific-parameter generation. Particularly, we first design a dual-path LoRA-based domain-aware adapter that disentangles features into domain-invariant and domain-specific components, enabling efficient adaptation. Additionally, a conditional diffusion-based parameter generation mechanism is presented to synthesize the adapter's parameters based on the current environment, preventing the optimization from getting stuck in local optima. Finally, we propose a class-centered optimal transport alignment method to mitigate catastrophic forgetting. Extensive experiments conducted on various continuous domain adaptive object detection tasks demonstrate the effectiveness. Meanwhile, visualization results show that the representation extracted by the generated parameters can capture more object-related information and strengthen the generalization ability. △ Less

Submitted 30 June, 2025; originally announced June 2025.

Aligning Spoken Dialogue Models from User Interactions

Authors: Anne Wu, Laurent Mazaré, Neil Zeghidour, Alexandre Défossez

Abstract: We propose a novel preference alignment framework for improving spoken dialogue models on real-time conversations from user interactions. Current preference learning methods primarily focus on text-based language models, and are not directly suited to the complexities of real-time speech interactions, with richer dynamics (e.g. interruption, interjection) and no explicit segmentation between speak… ▽ More We propose a novel preference alignment framework for improving spoken dialogue models on real-time conversations from user interactions. Current preference learning methods primarily focus on text-based language models, and are not directly suited to the complexities of real-time speech interactions, with richer dynamics (e.g. interruption, interjection) and no explicit segmentation between speaker turns.We create a large-scale dataset of more than 150,000 preference pairs from raw multi-turn speech conversations, annotated with AI feedback, to cover preferences over both linguistic content and temporal context variations. We leverage offline alignment methods to finetune a full-duplex autoregressive speech-to-speech model. Extensive experiments demonstrate that feedback on generic conversations can be consistently effective in improving spoken dialogue models to produce more factual, safer and more contextually aligned interactions. We deploy the finetuned model and conduct holistic human evaluations to assess the impact beyond single-turn conversations. Our findings shed light on the importance of a well-calibrated balance among various dynamics, crucial for natural real-time speech dialogue systems. △ Less

Submitted 26 June, 2025; originally announced June 2025.

Comments: Accepted at ICML 2025

OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography

Authors: Caoshuo Li, Zengmao Ding, Xiaobin Hu, Bang Li, Donghao Luo, AndyPian Wu, Chaoyang Wang, Chengjie Wang, Taisong Jin, SevenShu, Yunsheng Wu, Yongge Liu, Rongrong Ji

Abstract: As one of the earliest ancient languages, Oracle Bone Script (OBS) encapsulates the cultural records and intellectual expressions of ancient civilizations. Despite the discovery of approximately 4,500 OBS characters, only about 1,600 have been deciphered. The remaining undeciphered ones, with their complex structure and abstract imagery, pose significant challenges for interpretation. To address t… ▽ More As one of the earliest ancient languages, Oracle Bone Script (OBS) encapsulates the cultural records and intellectual expressions of ancient civilizations. Despite the discovery of approximately 4,500 OBS characters, only about 1,600 have been deciphered. The remaining undeciphered ones, with their complex structure and abstract imagery, pose significant challenges for interpretation. To address these challenges, this paper proposes a novel two-stage semantic typography framework, named OracleFusion. In the first stage, this approach leverages the Multimodal Large Language Model (MLLM) with enhanced Spatial Awareness Reasoning (SAR) to analyze the glyph structure of the OBS character and perform visual localization of key components. In the second stage, we introduce Oracle Structural Vector Fusion (OSVF), incorporating glyph structure constraints and glyph maintenance constraints to ensure the accurate generation of semantically enriched vector fonts. This approach preserves the objective integrity of the glyph structure, offering visually enhanced representations that assist experts in deciphering OBS. Extensive qualitative and quantitative experiments demonstrate that OracleFusion outperforms state-of-the-art baseline models in terms of semantics, visual appeal, and glyph maintenance, significantly enhancing both readability and aesthetic quality. Furthermore, OracleFusion provides expert-like insights on unseen oracle characters, making it a valuable tool for advancing the decipherment of OBS. △ Less

Submitted 26 June, 2025; originally announced June 2025.

Comments: Accepted to ICCV 2025

Case Study for Developing a UXR Point of View for FinOps Product Innovation

Authors: Jason Dong, Anna Wu

Abstract: In the dynamic landscape of Cloud financial management, we are sharing a case study exploring the development of a User Experience Research (UXR) Point of View (PoV) to drive FinOps product innovation. We demonstrate how qualitative and quantitative research methods working together to navigate the challenges of understanding customer needs, aligning cross-functional teams, and prioritizing limite… ▽ More In the dynamic landscape of Cloud financial management, we are sharing a case study exploring the development of a User Experience Research (UXR) Point of View (PoV) to drive FinOps product innovation. We demonstrate how qualitative and quantitative research methods working together to navigate the challenges of understanding customer needs, aligning cross-functional teams, and prioritizing limited resources. Through a multi-phased research approach, the research team identifies opportunities, quantifies pain points, and segments diverse customer cohorts. This culminated in a UXR PoV that informed the creation of a differentiated product strategy, a 'one-stop shop' dashboard empowering FinOps practitioners with actionable insights and tools. This case study highlights the power of mixed-methods research in uncovering actionable insights that drive impactful product innovation. △ Less

Submitted 18 June, 2025; originally announced June 2025.

Learning Task-Agnostic Motifs to Capture the Continuous Nature of Animal Behavior

Authors: Jiyi Wang, Jingyang Ke, Bo Dai, Anqi Wu

Abstract: Animals flexibly recombine a finite set of core motor motifs to meet diverse task demands, but existing behavior segmentation methods oversimplify this process by imposing discrete syllables under restrictive generative assumptions. To better capture the continuous structure of behavior generation, we introduce motif-based continuous dynamics (MCD) discovery, a framework that (1) uncovers interpre… ▽ More Animals flexibly recombine a finite set of core motor motifs to meet diverse task demands, but existing behavior segmentation methods oversimplify this process by imposing discrete syllables under restrictive generative assumptions. To better capture the continuous structure of behavior generation, we introduce motif-based continuous dynamics (MCD) discovery, a framework that (1) uncovers interpretable motif sets as latent basis functions of behavior by leveraging representations of behavioral transition structure, and (2) models behavioral dynamics as continuously evolving mixtures of these motifs. We validate MCD on a multi-task gridworld, a labyrinth navigation task, and freely moving animal behavior. Across settings, it identifies reusable motif components, captures continuous compositional dynamics, and generates realistic trajectories beyond the capabilities of traditional discrete segmentation models. By providing a generative account of how complex animal behaviors emerge from dynamic combinations of fundamental motor motifs, our approach advances the quantitative study of natural behavior. △ Less

Submitted 2 October, 2025; v1 submitted 18 June, 2025; originally announced June 2025.

Comments: 9 pages and 4 figures for the main text

Collaborative Editable Model

Authors: Kaiwen Tang, Aitong Wu, Yao Lu, Guangda Sun

Abstract: Vertical-domain large language models (LLMs) play a crucial role in specialized scenarios such as finance, healthcare, and law; however, their training often relies on large-scale annotated data and substantial computational resources, impeding rapid development and continuous iteration. To address these challenges, we introduce the Collaborative Editable Model (CoEM), which constructs a candidate… ▽ More Vertical-domain large language models (LLMs) play a crucial role in specialized scenarios such as finance, healthcare, and law; however, their training often relies on large-scale annotated data and substantial computational resources, impeding rapid development and continuous iteration. To address these challenges, we introduce the Collaborative Editable Model (CoEM), which constructs a candidate knowledge pool from user-contributed domain snippets, leverages interactive user-model dialogues combined with user ratings and attribution analysis to pinpoint high-value knowledge fragments, and injects these fragments via in-context prompts for lightweight domain adaptation. With high-value knowledge, the LLM can generate more accurate and domain-specific content. In a financial information scenario, we collect 15k feedback from about 120 users and validate CoEM with user ratings to assess the quality of generated insights, demonstrating significant improvements in domain-specific generation while avoiding the time and compute overhead of traditional fine-tuning workflows. △ Less

Submitted 16 June, 2025; originally announced June 2025.

Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel

Authors: Carlota Parés-Morlans, Michelle Yi, Claire Chen, Sarah A. Wu, Rika Antonova, Tobias Gerstenberg, Jeannette Bohg

Abstract: Tasks that involve complex interactions between objects with unknown dynamics make planning before execution difficult. These tasks require agents to iteratively improve their actions after actively exploring causes and effects in the environment. For these type of tasks, we propose Causal-PIK, a method that leverages Bayesian optimization to reason about causal interactions via a Physics-Informed… ▽ More Tasks that involve complex interactions between objects with unknown dynamics make planning before execution difficult. These tasks require agents to iteratively improve their actions after actively exploring causes and effects in the environment. For these type of tasks, we propose Causal-PIK, a method that leverages Bayesian optimization to reason about causal interactions via a Physics-Informed Kernel to help guide efficient search for the best next action. Experimental results on Virtual Tools and PHYRE physical reasoning benchmarks show that Causal-PIK outperforms state-of-the-art results, requiring fewer actions to reach the goal. We also compare Causal-PIK to human studies, including results from a new user study we conducted on the PHYRE benchmark. We find that Causal-PIK remains competitive on tasks that are very challenging, even for human problem-solvers. △ Less

Submitted 30 May, 2025; v1 submitted 28 May, 2025; originally announced May 2025.

Comments: Accepted to ICML 2025

Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environments

Authors: Junming Liu, Yanting Gao, Siyuan Meng, Yifei Sun, Aoqi Wu, Yufei Jin, Yirong Chen, Ding Wang, Guosun Zeng

Abstract: Federated Learning (FL) is a decentralized machine learning paradigm that enables clients to collaboratively train models while preserving data privacy. However, the coexistence of model and data heterogeneity gives rise to inconsistent representations and divergent optimization dynamics across clients, ultimately hindering robust global performance. To transcend these challenges, we propose Mosai… ▽ More Federated Learning (FL) is a decentralized machine learning paradigm that enables clients to collaboratively train models while preserving data privacy. However, the coexistence of model and data heterogeneity gives rise to inconsistent representations and divergent optimization dynamics across clients, ultimately hindering robust global performance. To transcend these challenges, we propose Mosaic, a novel data-free knowledge distillation framework tailored for heterogeneous distributed environments. Mosaic first trains local generative models to approximate each client's personalized distribution, enabling synthetic data generation that safeguards privacy through strict separation from real data. Subsequently, Mosaic forms a Mixture-of-Experts (MoE) from client models based on their specialized knowledge, and distills it into a global model using the generated data. To further enhance the MoE architecture, Mosaic integrates expert predictions via a lightweight meta model trained on a few representative prototypes. Extensive experiments on standard image classification benchmarks demonstrate that Mosaic consistently outperforms state-of-the-art approaches under both model and data heterogeneity. The source code has been published at https://github.com/Wings-Of-Disaster/Mosaic. △ Less

Submitted 26 May, 2025; originally announced May 2025.

Comments: 43 pages, 23 figures, 15 tables; the last dance

Generalizable cardiac substructures segmentation from contrast and non-contrast CTs using pretrained transformers

Authors: Aneesh Rangnekar, Nikhil Mankuzhy, Jonas Willmann, Chloe Choi, Abraham Wu, Maria Thor, Andreas Rimner, Harini Veeraraghavan

Abstract: Automated AI segmentations for radiation treatment planning deteriorate when applied to cases with different characteristics than the training dataset. We developed a hybrid transformer convolutional network to segment cardiac substructures in lung and breast cancer patients with varying imaging contrasts and scan positions. Cohort I (56 contrast-enhanced CT [CECT], 124 non-contrast CT [NCCT] scan… ▽ More Automated AI segmentations for radiation treatment planning deteriorate when applied to cases with different characteristics than the training dataset. We developed a hybrid transformer convolutional network to segment cardiac substructures in lung and breast cancer patients with varying imaging contrasts and scan positions. Cohort I (56 contrast-enhanced CT [CECT], 124 non-contrast CT [NCCT] scans from lung cancer patients, supine position) was used to train an oracle model (180 cases), contrast-only model (56 CECTs), and balanced model (32 CECT, 32 NCCT). All models were evaluated on 60 held-out cohort I patients and 66 cohort II breast cancer patients (45 supine, 21 prone). Accuracy was measured using Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), and dosimetric metrics, with TotalSegmentator as benchmark. Oracle and balanced models achieved similar accuracy (DSC: Oracle vs Balanced: Cohort I: 0.84 $\pm$ 0.10 vs 0.82 $\pm$ 0.10; Cohort II: 0.81 $\pm$ 0.12 vs 0.80 $\pm$ 0.13), both outperforming TotalSegmentator and the contrast-only models. The balanced model, using 64% fewer training cases, produced dosimetrically equivalent contours to manual delineations. It was robust to contrast variations (6 out of 8 substructures) and positioning variations (5 out of 8 substructures), with low correlation to patient age or body mass index. Our balanced model demonstrated robust geometric and dosimetric accuracy across varying imaging protocols and patient characteristics, which is essential for clinical deployment. Combining pretraining with balanced NCCT/CECT distribution enabled reliable segmentation with substantially fewer labeled cases than conventional approaches. △ Less

Submitted 26 November, 2025; v1 submitted 16 May, 2025; originally announced May 2025.

Sequential Treatment Effect Estimation with Unmeasured Confounders

Authors: Yingrong Wang, Anpeng Wu, Baohong Li, Ziyang Xiao, Ruoxuan Xiong, Qing Han, Kun Kuang

Abstract: This paper studies the cumulative causal effects of sequential treatments in the presence of unmeasured confounders. It is a critical issue in sequential decision-making scenarios where treatment decisions and outcomes dynamically evolve over time. Advanced causal methods apply transformer as a backbone to model such time sequences, which shows superiority in capturing long time dependence and per… ▽ More This paper studies the cumulative causal effects of sequential treatments in the presence of unmeasured confounders. It is a critical issue in sequential decision-making scenarios where treatment decisions and outcomes dynamically evolve over time. Advanced causal methods apply transformer as a backbone to model such time sequences, which shows superiority in capturing long time dependence and periodic patterns via attention mechanism. However, even they control the observed confounding, these estimators still suffer from unmeasured confounders, which influence both treatment assignments and outcomes. How to adjust the latent confounding bias in sequential treatment effect estimation remains an open challenge. Therefore, we propose a novel Decomposing Sequential Instrumental Variable framework for CounterFactual Regression (DSIV-CFR), relying on a common negative control assumption. Specifically, an instrumental variable (IV) is a special negative control exposure, while the previous outcome serves as a negative control outcome. This allows us to recover the IVs latent in observation variables and estimate sequential treatment effects via a generalized moment condition. We conducted experiments on 4 datasets and achieved significant performance in one- and multi-step prediction, supported by which we can identify optimal treatments for dynamic systems. △ Less

Submitted 13 May, 2025; originally announced May 2025.

Rethinking Few-Shot Image Fusion: Granular Ball Priors Enable General-Purpose Deep Fusion

Authors: Minjie Deng, Yan Wei, An Wu, Yuncan Ouyang, Hao Zhai, Qianyao Peng

Abstract: In image fusion tasks, the absence of real fused images as priors forces most deep learning approaches to rely on large-scale paired datasets to extract global weighting features or to generate pseudo-supervised images through algorithmic constructions. Unlike previous methods, this work re-examines prior-guided learning under few-shot conditions by introducing rough set theory. We regard the trad… ▽ More In image fusion tasks, the absence of real fused images as priors forces most deep learning approaches to rely on large-scale paired datasets to extract global weighting features or to generate pseudo-supervised images through algorithmic constructions. Unlike previous methods, this work re-examines prior-guided learning under few-shot conditions by introducing rough set theory. We regard the traditional algorithm as a prior generator, while the network re-inferrs and adaptively optimizes the prior through a dynamic loss function, reducing the inference burden of the network and enabling effective few-shot learning.To provide the prior, we propose the Granular Ball Pixel Computation (GBPC) algorithm. GBPC models pixel pairs in a luminance subspace using meta-granular balls and mines intra-ball information at multiple granular levels. At the fine-grained level, sliding granular balls assign adaptive weights to individual pixels to produce pixel-level prior fusion. At the coarse-grained level, the algorithm performs split computation within a single image to estimate positive and boundary domain distributions, enabling modality awareness and prior confidence estimation, which dynamically guide the loss weighting.The network and the algorithmic prior are coupled through the loss function to form an integrated framework. Thanks to the dynamic weighting mechanism, the network can adaptively adjust to different priors during training, enhancing its perception and fusion capability across modalities. We name this framework GBFF (Granular Ball Fusion Framework). Experiments on four fusion tasks demonstrate that even with only ten training image pairs per task, GBFF achieves superior performance in both visual quality and model compactness. Code is available at: https://github.com/DMinjie/GBFF △ Less

Submitted 9 December, 2025; v1 submitted 11 April, 2025; originally announced April 2025.

Clinical ModernBERT: An efficient and long context encoder for biomedical text

Authors: Simon A. Lee, Anthony Wu, Jeffrey N. Chiang

Abstract: We introduce Clinical ModernBERT, a transformer based encoder pretrained on large scale biomedical literature, clinical notes, and medical ontologies, incorporating PubMed abstracts, MIMIC IV clinical data, and medical codes with their textual descriptions. Building on ModernBERT the current state of the art natural language text encoder featuring architectural upgrades such as rotary positional e… ▽ More We introduce Clinical ModernBERT, a transformer based encoder pretrained on large scale biomedical literature, clinical notes, and medical ontologies, incorporating PubMed abstracts, MIMIC IV clinical data, and medical codes with their textual descriptions. Building on ModernBERT the current state of the art natural language text encoder featuring architectural upgrades such as rotary positional embeddings (RoPE), Flash Attention, and extended context length up to 8,192 tokens our model adapts these innovations specifically for biomedical and clinical domains. Clinical ModernBERT excels at producing semantically rich representations tailored for long context tasks. We validate this both by analyzing its pretrained weights and through empirical evaluation on a comprehensive suite of clinical NLP benchmarks. △ Less

Submitted 4 April, 2025; originally announced April 2025.

Comments: Manuscript writeup corresponding to the Clinical ModernBERT pre-trained encoder (https://huggingface.co/Simonlee711/Clinical_ModernBERT)

Orbit Determination through Cosmic Microwave Background Radiation

Authors: Pedro K de Albuquerque, Andre R Kuroswiski, Annie S. Wu, Willer G. dos Santos, Paulo Costa

Abstract: This research explores the use of Cosmic Microwave Background (CMB) radiation as a reference signal for Initial Orbit Determination (IOD). By leveraging the unique properties of CMB, this study introduces a novel method for estimating spacecraft velocity and position with minimal reliance on pre-existing environmental data, offering significant advantages for space missions independent of Earth-sp… ▽ More This research explores the use of Cosmic Microwave Background (CMB) radiation as a reference signal for Initial Orbit Determination (IOD). By leveraging the unique properties of CMB, this study introduces a novel method for estimating spacecraft velocity and position with minimal reliance on pre-existing environmental data, offering significant advantages for space missions independent of Earth-specific conditions. Using Machine Learning (ML) regression models, this approach demonstrates the capability to determine velocity from CMB signals and subsequently determine the satellite's position. The results indicate that CMB has the potential to enhance the autonomy and flexibility of spacecraft operations. △ Less

Submitted 2 April, 2025; originally announced April 2025.

Comments: This paper was presented at the 2024 AAS/AIAA Astrodynamics Specialist Conference, August 11-15, 2024, Broomfield, Colorado, USA

Graph-Based Uncertainty-Aware Self-Training with Stochastic Node Labeling

Authors: Tom Liu, Anna Wu, Chao Li

Abstract: Self-training has become a popular semi-supervised learning technique for leveraging unlabeled data. However, the over-confidence of pseudo-labels remains a key challenge. In this paper, we propose a novel \emph{graph-based uncertainty-aware self-training} (GUST) framework to combat over-confidence in node classification. Drawing inspiration from the uncertainty integration idea introduced by Wang… ▽ More Self-training has become a popular semi-supervised learning technique for leveraging unlabeled data. However, the over-confidence of pseudo-labels remains a key challenge. In this paper, we propose a novel \emph{graph-based uncertainty-aware self-training} (GUST) framework to combat over-confidence in node classification. Drawing inspiration from the uncertainty integration idea introduced by Wang \emph{et al.}~\cite{wang2024uncertainty}, our method largely diverges from previous self-training approaches by focusing on \emph{stochastic node labeling} grounded in the graph topology. Specifically, we deploy a Bayesian-inspired module to estimate node-level uncertainty, incorporate these estimates into the pseudo-label generation process via an expectation-maximization (EM)-like step, and iteratively update both node embeddings and adjacency-based transformations. Experimental results on several benchmark graph datasets demonstrate that our GUST framework achieves state-of-the-art performance, especially in settings where labeled data is extremely sparse. △ Less

Submitted 29 July, 2025; v1 submitted 26 March, 2025; originally announced March 2025.

Comments: arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship and affiliation

Progressive Human Motion Generation Based on Text and Few Motion Frames

Authors: Ling-An Zeng, Gaojie Wu, Ancong Wu, Jian-Fang Hu, Wei-Shi Zheng

Abstract: Although existing text-to-motion (T2M) methods can produce realistic human motion from text description, it is still difficult to align the generated motion with the desired postures since using text alone is insufficient for precisely describing diverse postures. To achieve more controllable generation, an intuitive way is to allow the user to input a few motion frames describing precise desired… ▽ More Although existing text-to-motion (T2M) methods can produce realistic human motion from text description, it is still difficult to align the generated motion with the desired postures since using text alone is insufficient for precisely describing diverse postures. To achieve more controllable generation, an intuitive way is to allow the user to input a few motion frames describing precise desired postures. Thus, we explore a new Text-Frame-to-Motion (TF2M) generation task that aims to generate motions from text and very few given frames. Intuitively, the closer a frame is to a given frame, the lower the uncertainty of this frame is when conditioned on this given frame. Hence, we propose a novel Progressive Motion Generation (PMG) method to progressively generate a motion from the frames with low uncertainty to those with high uncertainty in multiple stages. During each stage, new frames are generated by a Text-Frame Guided Generator conditioned on frame-aware semantics of the text, given frames, and frames generated in previous stages. Additionally, to alleviate the train-test gap caused by multi-stage accumulation of incorrectly generated frames during testing, we propose a Pseudo-frame Replacement Strategy for training. Experimental results show that our PMG outperforms existing T2M generation methods by a large margin with even one given frame, validating the effectiveness of our PMG. Code is available at https://github.com/qinghuannn/PMG. △ Less

Submitted 30 March, 2025; v1 submitted 17 March, 2025; originally announced March 2025.

Comments: Accepted to IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025

EmoBipedNav: Emotion-aware Social Navigation for Bipedal Robots with Deep Reinforcement Learning

Authors: Wei Zhu, Abirath Raju, Abdulaziz Shamsah, Anqi Wu, Seth Hutchinson, Ye Zhao

Abstract: This study presents an emotion-aware navigation framework -- EmoBipedNav -- using deep reinforcement learning (DRL) for bipedal robots walking in socially interactive environments. The inherent locomotion constraints of bipedal robots challenge their safe maneuvering capabilities in dynamic environments. When combined with the intricacies of social environments, including pedestrian interactions a… ▽ More This study presents an emotion-aware navigation framework -- EmoBipedNav -- using deep reinforcement learning (DRL) for bipedal robots walking in socially interactive environments. The inherent locomotion constraints of bipedal robots challenge their safe maneuvering capabilities in dynamic environments. When combined with the intricacies of social environments, including pedestrian interactions and social cues, such as emotions, these challenges become even more pronounced. To address these coupled problems, we propose a two-stage pipeline that considers both bipedal locomotion constraints and complex social environments. Specifically, social navigation scenarios are represented using sequential LiDAR grid maps (LGMs), from which we extract latent features, including collision regions, emotion-related discomfort zones, social interactions, and the spatio-temporal dynamics of evolving environments. The extracted features are directly mapped to the actions of reduced-order models (ROMs) through a DRL architecture. Furthermore, the proposed framework incorporates full-order dynamics and locomotion constraints during training, effectively accounting for tracking errors and restrictions of the locomotion controller while planning the trajectory with ROMs. Comprehensive experiments demonstrate that our approach exceeds both model-based planners and DRL-based baselines. The hardware videos and open-source code are available at https://gatech-lidar.github.io/emobipednav.github.io/. △ Less

Submitted 16 March, 2025; originally announced March 2025.

Comments: 13 pages

Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection

Authors: Zihao Zhang, Aming Wu, Yahong Han

Abstract: Recently, a task of Single-Domain Generalized Object Detection (Single-DGOD) is proposed, aiming to generalize a detector to multiple unknown domains never seen before during training. Due to the unavailability of target-domain data, some methods leverage the multimodal capabilities of vision-language models, using textual prompts to estimate cross-domain information, enhancing the model's general… ▽ More Recently, a task of Single-Domain Generalized Object Detection (Single-DGOD) is proposed, aiming to generalize a detector to multiple unknown domains never seen before during training. Due to the unavailability of target-domain data, some methods leverage the multimodal capabilities of vision-language models, using textual prompts to estimate cross-domain information, enhancing the model's generalization capability. These methods typically use a single textual prompt, often referred to as the one-step prompt method. However, when dealing with complex styles such as the combination of rain and night, we observe that the performance of the one-step prompt method tends to be relatively weak. The reason may be that many scenes incorporate not just a single style but a combination of multiple styles. The one-step prompt method may not effectively synthesize combined information involving various styles. To address this limitation, we propose a new method, i.e., Style Evolving along Chain-of-Thought, which aims to progressively integrate and expand style information along the chain of thought, enabling the continual evolution of styles. Specifically, by progressively refining style descriptions and guiding the diverse evolution of styles, this approach enables more accurate simulation of various style characteristics and helps the model gradually learn and adapt to subtle differences between styles. Additionally, it exposes the model to a broader range of style features with different data distributions, thereby enhancing its generalization capability in unseen domains. The significant performance gains over five adverse-weather scenarios and the Real to Art benchmark demonstrate the superiorities of our method. △ Less

Submitted 12 March, 2025; originally announced March 2025.

Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling

Authors: Long Peng, Anran Wu, Wenbo Li, Peizhe Xia, Xueyuan Dai, Xinjie Zhang, Xin Di, Haoze Sun, Renjing Pei, Yang Wang, Yang Cao, Zheng-Jun Zha

Abstract: Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained to fixed-scale factors (\textit{e.g.}, $\times$ 2). Recent advances leveraging implicit neural representation (INR) have achieved great progress by modeling co… ▽ More Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained to fixed-scale factors (\textit{e.g.}, $\times$ 2). Recent advances leveraging implicit neural representation (INR) have achieved great progress by modeling coordinate-to-pixel mappings. However, the efficiency of these methods may suffer from repeated upsampling and decoding, while their reconstruction fidelity and quality are constrained by the intrinsic representational limitations of coordinate-based functions. To address these challenges, we propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting. This approach eliminates the need for time-consuming upsampling and decoding, enabling extremely fast arbitrary-scale super-resolution. Once the Gaussian field is built in a single pass, ContinuousSR can perform arbitrary-scale rendering in just 1ms per scale. Our method introduces several key innovations. Through statistical ana △ Less

Submitted 9 March, 2025; originally announced March 2025.

Comments: Tech Report