Showing 1–50 of 158 results for author: Tao, L

Difference-of-Convex Regularization for Graph Learning by Differentiable Programming

Authors: Liping Tao, Chee Wei Tan

Abstract: Laplacian-regularized minimization is fundamental in signal processing and machine learning, but is limited by the dense and ill-conditioned nature of the graph Laplacian pseudoinverse. While the Laplacian itself is sparse, its pseudoinverse is dense and often ill-conditioned, rendering direct computation impractical at scale. Moreover, pseudoinverse learning is more challenging than Laplacian lea… ▽ More Laplacian-regularized minimization is fundamental in signal processing and machine learning, but is limited by the dense and ill-conditioned nature of the graph Laplacian pseudoinverse. While the Laplacian itself is sparse, its pseudoinverse is dense and often ill-conditioned, rendering direct computation impractical at scale. Moreover, pseudoinverse learning is more challenging than Laplacian learning. To address this challenge, this paper considers the setting where the graph Laplacian is given and proposes a Difference-of-Convex Regularizer (DCR) graph learning framework that approximates the spectral action of the Laplacian pseudoinverse without direct inversion via regularized Maximum Likelihood Estimation (MLE). By reformulating Laplacian-Regularized Nonnegative Least Squares (LR-NNLS) through a dual representation, DCR decouples pseudoinverse learning from instance-specific inference and enables efficient primal solution reconstruction via a differentiable dual-guided learning scheme. We establish theoretical guarantees on stability and the existence of a unique fixed point for DCR algorithm. Numerical experiments demonstrate improved performance over convex solvers and graph filtering baselines and robust performance across diverse graph topologies. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Diversifying Personalized Research Ideation against AI-Induced Homogenization

Authors: Rui Xu, Yunke Wang, Linwei Tao, Wenjie Xuan, Yong Luo

Abstract: AI-assisted research ideation has emerged as a promising paradigm for accelerating scientific discovery, with systems now capable of generating research directions conditioned on papers, topics, or lightweight researcher contexts. Yet current systems largely optimize individual suggestions in isolation. This leaves two blind spots. First, coarse researcher representations may elicit mainstream dir… ▽ More AI-assisted research ideation has emerged as a promising paradigm for accelerating scientific discovery, with systems now capable of generating research directions conditioned on papers, topics, or lightweight researcher contexts. Yet current systems largely optimize individual suggestions in isolation. This leaves two blind spots. First, coarse researcher representations may elicit mainstream directions that appear broadly feasible, but lack sufficient researcher-specific grounding. Second, independent recommendations can concentrate a community's portfolio around recurring high-probability themes. To address these blind spots, we propose DivAlign, a four-stage pipeline for alignment-preserving de-homogenization. DivAlign extracts fine-grained researcher profiles, generates profile-conditioned candidate directions, scores them along three alignment dimensions (Executability, Comprehensibility, and Growth Potential), and surfaces researcher-local directions while reducing redundancy across the community portfolio. On a benchmark we construct from 95 AI researchers across five subfields, DivAlign reduces community-level redundancy while preserving researcher-direction fit. Compared with coarse single-shot ideation, it lowers average pairwise similarity from 0.331 to 0.294 and nearest-neighbor similarity from 0.704 to 0.608. Compared with the independent top-choice variant, DivAlign reduces nearest-neighbor similarity from 0.663 to 0.608 while retaining 99.9% of the researcher-direction fit score. Code and data are available at https://github.com/Ruixxxx/DivAlign. △ Less

Submitted 30 July, 2026; originally announced July 2026.

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents

Authors: Leitian Tao, Baolin Peng, Wenlin Yao, Tao Ge, Hao Cheng, Mike Hang Wang, Jianfeng Gao, Sharon Li

Abstract: Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training. Outcome rewards provide reliable supervision for short-horizon reasoning, but become sparse and high-variance as trajectories grow to tens or hundreds of tool calls. They can also be misleading: a failed rollou… ▽ More Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training. Outcome rewards provide reliable supervision for short-horizon reasoning, but become sparse and high-variance as trajectories grow to tens or hundreds of tool calls. They can also be misleading: a failed rollout may contain many useful actions that move the agent closer to the goal, yet outcome-only training assigns them the same negative advantage as the eventual mistake. We propose TRACE (Turn-level Reward Assignment via Credit Estimation), a dense credit-assignment method for agentic reinforcement learning. TRACE represents rollouts as state transitions at tool-call boundaries, obtains gold-answer log-probabilities from a frozen reference model, transforms them into log-ratio state values, and derives per-action rewards as Temporal-Difference changes in those values. This requires no additional critic or process-label training, and its one-step log-ratio TD component telescopes across redundant tool calls. On long-horizon complex search, TRACE substantially improves base-model tool-use ability using pure RL, without a cold-start supervised fine-tuning stage, an agentic mid-training stage, or training on live-web data. On the closed-web BrowseComp-Plus benchmark, it raises Qwen3-4B from $7.2$ to $35.6$ and Qwen3-30B-A3B from $8.4$ to $42.6$. The learned search behavior also transfers to open-web benchmarks, and the learning curves show earlier improvement and faster convergence during RL training. △ Less

Submitted 15 July, 2026; originally announced July 2026.

Comments: 26 pages

Diffusion learning reveals viable parameter manifolds and compensation geometry in biological dynamical systems

Authors: Ruilin Zhang, Louis Tao, Zhuo-Cheng Xiao

Abstract: Models of complex systems often have many parameters, yet are constrained by far fewer experimentally accessible observables: similar activity can emerge from coordinated parameter changes. We formalize these compatible parameter sets as \emph{viable parameter manifolds}: the inverse images of a system's target dynamical behaviors under a parameter-to-feature map. The relevant codimension is not t… ▽ More Models of complex systems often have many parameters, yet are constrained by far fewer experimentally accessible observables: similar activity can emerge from coordinated parameter changes. We formalize these compatible parameter sets as \emph{viable parameter manifolds}: the inverse images of a system's target dynamical behaviors under a parameter-to-feature map. The relevant codimension is not the number of reported features, but the effective rank of that map at the target scale. Co-varying features lower the codimension, while poor conditioning, high curvature, or regime mixing degrade learnability. We train conditional score-based diffusion models on simulated parameter--feature pairs and use them as amortized samplers of prior-weighted viable sets. In the Lorenz system, scalar trajectory statistics generate thin viable sheets, and two-feature conditioning localizes a transition-adjacent corridor. In the Izhikevich neuron model, four firing descriptors lie close to a nearly two-dimensional family of features, and the learned inverse images reveal distinct regular and irregular compensation geometries. In a recent ODE reduction of finite spiking networks, the same framework reveals excitatory--inhibitory compensation, timescale--coupling tradeoffs, and input-dependent viable manifolds across 4--12 parameter dimensions. In this view, robustness, compensation, and hidden parameter dependencies are organized as inverse geometry, with diffusion models providing practical tools for sampling, visualizing, and interrogating that geometry. △ Less

Submitted 3 July, 2026; originally announced July 2026.

Comments: 25 pages, 7 figures

FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion

Authors: Guanchen Lu, Yajuan Dun, Yi Zhou, Letian Tao, Jingliang Duan, Jie Li, Guofa Li

Abstract: Scalable reinforcement learning has popularized high-throughput sampling architectures, which significantly compresses the training time for off-policy methods in robotic locomotion. However, the rapid increase of data volume and update frequency undermines the stability of value-based methods and diminishes the plasticity of policy networks. To address these challenges, this work presents FastDSA… ▽ More Scalable reinforcement learning has popularized high-throughput sampling architectures, which significantly compresses the training time for off-policy methods in robotic locomotion. However, the rapid increase of data volume and update frequency undermines the stability of value-based methods and diminishes the plasticity of policy networks. To address these challenges, this work presents FastDSAC, a fast and high-performance variant of the Distributional Actor-Critic algorithm designed for parallel sampling scenarios. Specifically, we introduce a truncated Gaussian distribution to approximate the learned policy, which effectively excludes out-of-distribution actions that strain target value estimation while keeping necessary stochasticity for exploration. The proposed action constraint functions as an implicit regularization, which counteracts the plasticity loss typically caused by aggressive gradient updates. This preservation of network adaptability enhances sample efficiency, particularly in scenarios with a high update-to-data ratio, and accelerates the early training process. In contrast to prior fast reinforcement learning approaches that rely on discrete value distributions, our method utilizes a continuous Gaussian representation equipped with adaptive variance regulation, which improves value estimation accuracy by sampling confident and informative transitions. Extensive experiments on MuJoCo Playground and HumanoidBench demonstrate that FastDSAC not only stabilizes the overall training process but also achieves superior asymptotic performance and faster convergence compared to state-of-the-art baselines. △ Less

Submitted 30 June, 2026; originally announced June 2026.

Comments: 8 pages, 9 figures. Code is available at https://github.com/luge66/FastDSAC

Heterogeneous synaptic motifs bridge microscale structure and macroscale nonlinear dynamics

Authors: Meiyi Zhang, Jinjian Yu, Louis Tao, Yuxiu Shao

Abstract: Recent breakthroughs in synaptic-resolution network connectomics have revealed that brain circuits feature fine-scale structural connectivity, such as pairs of correlated synaptic couplings known as second-order motifs. Large-scale recordings of neuronal activity in networks containing nonlinear neurons reveal macroscopic heterogeneous population dynamics throughout the brain. These findings rekin… ▽ More Recent breakthroughs in synaptic-resolution network connectomics have revealed that brain circuits feature fine-scale structural connectivity, such as pairs of correlated synaptic couplings known as second-order motifs. Large-scale recordings of neuronal activity in networks containing nonlinear neurons reveal macroscopic heterogeneous population dynamics throughout the brain. These findings rekindle the inquiry into this intriguing question: Can microscale synaptic structures contribute to macroscopic heterogeneous dynamics and computations in ways that canonical brain circuit models cannot? To answer this question, we create random RNNs with various cell types, nonlinear non-negative neural responses, and arbitrary marginal and second-order correlated synaptic statistics. We derive mean-field low-rank equations for P-population networks in which the pre- and postsynaptic neuronal population identities determine the synaptic and motif strengths. Our framework requires 2P latent dynamic variables with P variables describing mean population activity and P variables capturing within-population variability. Theoretical and simulational results demonstrate that chain motifs induce correlations in synaptic variability, enabling microscopic fluctuations to be integrated and influence mesoscopic mean population dynamics. We apply this framework to reverse engineer network connectivity that recapitulates the heterogeneous activity across the population in the mouse primary visual cortex. By bridging the gap between synaptic organization and nonlinear heterogeneous population dynamics, our results offer a principled approach and testable predictions regarding the relationship between fine-scale connectivity, heterogeneous dynamics, and functional computations. △ Less

Submitted 26 June, 2026; originally announced June 2026.

Comments: 36 pages, 14 figures

FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving

Authors: Bonan Wang, Letian Tao, Bin Shuai, Jiaxin Gao, Wenxin Zhao, Wei Xiong, Kehua Sheng, Bo Zhang, Yang Guan, Shengbo Eben Li

Abstract: Deep reinforcement learning is pivotal for closed-loop autonomous driving yet remains constrained by severe bottlenecks in sampling efficiency. Standard parallel sampling mitigates this but suffers from the straggler effect, where the premature termination of a single environment necessitates a synchronized batch re-initialization, leading to suboptimal sample utilization and prohibitive re-initia… ▽ More Deep reinforcement learning is pivotal for closed-loop autonomous driving yet remains constrained by severe bottlenecks in sampling efficiency. Standard parallel sampling mitigates this but suffers from the straggler effect, where the premature termination of a single environment necessitates a synchronized batch re-initialization, leading to suboptimal sample utilization and prohibitive re-initialization latency. To address this, we propose FAST, a synchronous parallel framework tailored for closed-loop simulation. Specifically, FAST employs Dynamic Parallel Sampling Alignment (DPSA) to maintain vectorization synchronization by extending terminated episodes via virtual continuation, thereby decoupling the sampling loop from individual terminations. By dynamically triggering global truncation based on the termination rate of parallel clips, FAST effectively eliminates the bottleneck of premature resets without sacrificing data diversity. Furthermore, to strictly preserve theoretical consistency, we incorporate a Scaled Mask-Padding Optimization (SMPO) that leverages validity masking and adaptive loss normalization to nullify the bias from auxiliary padding data. Empirical evaluations demonstrate that FAST achieves at least a 1.78 times wall-clock speedup over the single-clip baseline while preserving statistical unbiasedness. △ Less

Submitted 13 July, 2026; v1 submitted 19 June, 2026; originally announced June 2026.

Dynamic Execution Horizon Prediction for Chunk-based Robot Policies

Authors: Yuchi Zhao, Miroslav Bogdanovic, Arjun Sohal, Liyu Tao, Kourosh Darvish, Alán Aspuru-Guzik, Florian Shkurti, Animesh Garg

Abstract: Action chunking has become a standard design in modern robot policies, from diffusion/flow policies to vision-language-action models, where the policy predicts a sequence of actions and executes a fixed number of them instead of acting one step at a time. However, this paradigm relies on a key assumption: a fixed execution horizon. During chunk execution, the policy operates open-loop, which is pa… ▽ More Action chunking has become a standard design in modern robot policies, from diffusion/flow policies to vision-language-action models, where the policy predicts a sequence of actions and executes a fixed number of them instead of acting one step at a time. However, this paradigm relies on a key assumption: a fixed execution horizon. During chunk execution, the policy operates open-loop, which is particularly problematic for fine-grained manipulation tasks that require frequent replanning. In practice, the execution horizon is typically chosen through empirical tuning and is highly task-dependent. To this end, we propose Dynamic Execution Horizon Prediction (DEHP), an effective method that trains a lightweight execution-horizon prediction branch using online reinforcement learning while keeping the pretrained chunk policy completely frozen. This makes the method compatible with black-box chunk policies and isolates the effect of adapting the execution horizon from changes to the underlying action generator. Across our evaluations, DEHP improves the success rate of different high-precision and long-horizon manipulation tasks by a large margin. Our qualitative analysis further shows that DEHP predicts shorter execution horizons during fine-grained stages of the task and longer horizons during free-space motion. In this way, DEHP balances the efficiency of open-loop chunk execution with the reactivity of closed-loop single-step control. Project page: https://dehp-chunking.github.io/ △ Less

Submitted 9 July, 2026; v1 submitted 9 June, 2026; originally announced June 2026.

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

Authors: Renjie Mao, Xiangxin Zhou, Lvfang Tao, Yixin Ding, Yu Shi, Yongguang Lin, Yuheng Wu, Honglin Zhu, Qian Qiu, Wenxi Zhu

Abstract: Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechanisms remain position-agnostic by enforcing uniform thresholds across all tokens independently. This pointwise treatment conflicts with autoregressive generation in two critical ways. First, uniform thresholds ignore autoregressive asymmetry. Early-st… ▽ More Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechanisms remain position-agnostic by enforcing uniform thresholds across all tokens independently. This pointwise treatment conflicts with autoregressive generation in two critical ways. First, uniform thresholds ignore autoregressive asymmetry. Early-stage deviations produce compounding sequence-level drift, causing static thresholds to under-regulate early divergence and excessively constrain late-stage exploration. Second, evaluating token-level divergence in isolation overlooks cumulative prefix drift, granting the same divergence allowance regardless of how far the conditioning history has already deviated from the rollout policy. To address this limitation, we propose CPPO (Cumulative Prefix-divergence Policy Optimization), a token-level masking rule that aligns updates with a finite-horizon policy-improvement bound via two coupled mechanisms. First, a position-weighted threshold imposes stricter limits at early positions whose effects persist longer, relaxing constraints for late-stage tokens. Second, a cumulative prefix budget tracks historical deviations, dynamically restricting further token-level deviation to prevent compounding errors along the prefix. Empirically, CPPO enhances training stability and significantly improves reasoning accuracy across various model scales. △ Less

Submitted 10 June, 2026; v1 submitted 9 June, 2026; originally announced June 2026.

Comments: Project Page: https://hunyuan-cppo.github.io/

DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction

Authors: Reazul Hasan Russel, Mingwei Tang, Rostam Shirani, Xinlong Liu, Navid Madani, Leo Ding, Yawen He, Xiangyu Wang, Mustafa Acar, Ashish Katiyar, Yuhai Li, Alan Yang, Metarya Ruparel, Derek Qiang Xu, Rupert Wu, Rui Yang, Liang Tao, Xinyi Zhao, Larry Zhang, Sri Reddy, Rob Malkin

Abstract: Offsite conversion rate (OCVR) prediction is an important ranking problem in computational recommendation systems. This task presents a modeling challenge: click signals are abundant and exhibit short temporal horizons, whereas conversion signals are inherently sparse, long-delayed, and frequently unattributed. Despite these statistical disparities, both signal types must inform models that operat… ▽ More Offsite conversion rate (OCVR) prediction is an important ranking problem in computational recommendation systems. This task presents a modeling challenge: click signals are abundant and exhibit short temporal horizons, whereas conversion signals are inherently sparse, long-delayed, and frequently unattributed. Despite these statistical disparities, both signal types must inform models that operate within strict serving-latency constraints. Prior pre-training approaches address this heterogeneity with a single, undifferentiated encoder applied uniformly across both data streams. We propose DUET (Dual User Embedding Transformers), a framework that explicitly partitions user behavioral data into two domain-coherent streams -- clicks and conversions -- and pre-trains dedicated transformer encoders with architectures tailored to each stream's statistical characteristics: multi-layer self-attention for the dense click stream and interleaved cross- and self-attention for the sparse conversion stream. The resulting complementary embeddings are jointly consumed by a downstream ranker without exceeding serving-latency budgets. Evaluation demonstrates up to 0.38% normalized entropy (NE) reduction relative to the strongest baseline, and A/B test shows consistent improvements in OCVR prediction accuracy. △ Less

Submitted 8 June, 2026; originally announced June 2026.

Retrieval-Augmented Linguistic Calibration

Authors: Yi-Fan Yeh, Linwei Tao, Minjing Dong, Tao Huang, Jialin Yu, Philip Torr, Chang Xu

Abstract: Linguistic cues such as "I believe" and "probably" offer an intuitive interface for communicating confidence, yet a generalisable, principled calibration framework for linguistic confidence expressions remains underexplored. In particular, co-occurring linguistic cues, contextual variation, and subjective audience interpretation pose unique challenges. We therefore model linguistic confidence as a… ▽ More Linguistic cues such as "I believe" and "probably" offer an intuitive interface for communicating confidence, yet a generalisable, principled calibration framework for linguistic confidence expressions remains underexplored. In particular, co-occurring linguistic cues, contextual variation, and subjective audience interpretation pose unique challenges. We therefore model linguistic confidence as a distribution over plausible perceived probability values that a statement is correct, capturing interpretation variability that scalar representations discard. Within this distributional framework, we introduce faithfulness as a complementary evaluation dimension and present Faithfulness Divergence (FD), an information-theoretic metric quantifying the surprise induced in audience beliefs upon truth revelation. Building on these foundations, we present Retrieval-Augmented Linguistic Calibration (RALC), a lightweight post-hoc pipeline that propagates calibrated confidence signals back into natural language via retrieval-augmented rewriting. Across three QA benchmarks and five LLM families, RALC improves in-domain faithfulness and calibration up to 66% and 58%, respectively, outperforming black-box and grey-box calibration baselines. △ Less

Submitted 29 May, 2026; v1 submitted 19 May, 2026; originally announced May 2026.

Learning-Based Spectrum Cartography in Low Earth Orbit Satellite Networks: An Overview

Authors: Liping Tao, Xindi Tong, Chee Wei Tan

Abstract: Low earth orbit (LEO) satellite networks are emerging as a key infrastructure for global connectivity and space-based sensing. Many tasks in such systems can be formulated as measurement-set-to-spatial-inference problems, where spatial variables are inferred from sparse and heterogeneous wireless observations. Spectrum cartography provides a unifying framework for this paradigm, encompassing repre… ▽ More Low earth orbit (LEO) satellite networks are emerging as a key infrastructure for global connectivity and space-based sensing. Many tasks in such systems can be formulated as measurement-set-to-spatial-inference problems, where spatial variables are inferred from sparse and heterogeneous wireless observations. Spectrum cartography provides a unifying framework for this paradigm, encompassing representative tasks such as satellite-assisted localization and radio map reconstruction, as well as map-informed resource allocation. Yet the highly dynamic orbital geometry, complex propagation conditions, and reliability-varying nature of LEO measurements pose fundamental challenges for traditional model-driven and interpolation-based methods. This article surveys the literature from 1964 to 2026 on learning-based spectrum cartography as applied to LEO satellite networks, with a particular focus on attention mechanisms as a principled operator for adaptive and reliability-aware measurement fusion across localization, radio map reconstruction, and resource allocation tasks. We review modeling foundations and key challenges of representative tasks, and analyze how attention-based learning enables flexible fusion of heterogeneous measurements for both inference and map-informed decision-making. Representative formulations and simulation studies are provided to illustrate the framework and demonstrate its effectiveness, offering a unified perspective for measurement-driven inference and decision-making in LEO satellite networks. △ Less

Submitted 11 May, 2026; originally announced May 2026.

Terrain Perception for Agricultural UAVs in Complex Farmland via Rotating mmWave Radar

Authors: Zhihao Zhan, Le Tao, Shaobin Li, Chenxin Fang, Xingrui Yang, Liang Li, Rui Fan, Yuhang Ming

Abstract: Accurate terrain perception is essential for terrain-following flight of agricultural unmanned aerial vehicles (UAVs), yet remains challenging in real-world farmland due to occlusions, complex terrain geometry, and environmental disturbances. Millimeter-wave (mmWave) radar is a promising sensing modality for this task due to its robustness to adverse conditions; however, existing UAV-mounted radar… ▽ More Accurate terrain perception is essential for terrain-following flight of agricultural unmanned aerial vehicles (UAVs), yet remains challenging in real-world farmland due to occlusions, complex terrain geometry, and environmental disturbances. Millimeter-wave (mmWave) radar is a promising sensing modality for this task due to its robustness to adverse conditions; however, existing UAV-mounted radar systems rely on fixed field of view (FoV) and terrain extraction methods designed for dense LiDAR data, leading to incomplete and unreliable terrain estimation. To address these limitations, we present a low-cost rotating mmWave radar-enabled terrain perception framework for agricultural UAVs operating in complex farmland environments. Specifically, a mechanically rotating sensing design is introduced to enlarge spatial coverage and improve terrain observability beyond the limitations of fixed-view radar under dynamic low-altitude flight. Building upon this sensing capability, we further design a pose-consistent terrain reconstruction pipeline tailored for sparse, noisy, and partially observable radar data, enabling reliable ground extraction and continuous terrain surface estimation in challenging agricultural scenarios. The complete system is deployed on a real agricultural UAV platform and comprehensively evaluated through extensive field experiments. Experimental results demonstrate improved terrain coverage and estimation accuracy, achieving an F1 score of 94.42 for ground segmentation, while the closest rival only achieves 90.48. Thus, leading to more robust terrain following flight. △ Less

Submitted 2 May, 2026; originally announced May 2026.

Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving

Authors: Xinyu Zeng, Xiangkun He, Lei Tao, Chen Lv, Hong Cheng

Abstract: Autonomous driving (AD) is evolving towards end-to-end (E2E) frameworks through two primary paradigms: monolithic models exemplified by Vision-Language-Action (VLA), and specialized modular architectures. Despite their divergent designs, both paradigms increasingly rely on Transformer backbones for complex reasoning, potentially causing a shared vulnerability: visually imperceptible perturbations… ▽ More Autonomous driving (AD) is evolving towards end-to-end (E2E) frameworks through two primary paradigms: monolithic models exemplified by Vision-Language-Action (VLA), and specialized modular architectures. Despite their divergent designs, both paradigms increasingly rely on Transformer backbones for complex reasoning, potentially causing a shared vulnerability: visually imperceptible perturbations can manipulate E2E AD models into hazardous maneuvers by targeting the Transformer module. Most existing adversarial attack approaches against AD systems operate under white-box or black-box settings; yet, they typically necessitate full model transparency, or suffer from either prohibitive query latency or limited attack transferability. In this paper, we propose Adversarial Flow Matching (AFM), a novel gray-box attack framework that exploits Transformer structural vulnerabilities in E2E AD models. AFM enables efficient one-step generation of adversarial examples via a neural average velocity field. Additionally, the proposed technique yields effective and visually imperceptible attacks by synergistically perturbing the generative latent space and the neural average velocity field. Extensive experiments demonstrate that AFM achieves a superior trade-off between attack effectiveness and imperceptibility: it substantially degrades the performance of both VLA and modular AD agents across various scenarios compared to baselines, while maintaining state-of-the-art visual imperceptibility. Furthermore, adversarial examples generated by AFM exhibit robust cross-model transferability, indicating that AFM closely approximates a black-box attack setting while requiring only the prior knowledge that the target AD model incorporates a Transformer-based module. △ Less

Submitted 26 April, 2026; originally announced May 2026.

Comments: 16 pages, 11 figures

IAM: Identity-Aware Human Motion and Shape Joint Generation

Authors: Wenqi Jia, Zekun Li, Abhay Mittal, Chengcheng Tang, Chuan Guo, Lezi Wang, James Matthew Rehg, Lingling Tao, Size An

Abstract: Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. However, most existing approaches assume identity-neutral motion and generate movements using a canonical body representation, ignoring the strong influence of body morphology on motion dynamics. In practice, attributes such as body proportions, mass dis… ▽ More Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. However, most existing approaches assume identity-neutral motion and generate movements using a canonical body representation, ignoring the strong influence of body morphology on motion dynamics. In practice, attributes such as body proportions, mass distribution, and age significantly affect how actions are performed, and neglecting this coupling often leads to physically inconsistent motions. We propose an identity-aware motion generation framework that explicitly models the relationship between body morphology and motion dynamics. Instead of relying on explicit geometric measurements, identity is represented using multimodal signals, including natural language descriptions and visual cues. We further introduce a joint motion-shape generation paradigm that simultaneously synthesizes motion sequences and body shape parameters, allowing identity cues to directly modulate motion dynamics. Extensive experiments on motion capture datasets and large-scale in-the-wild videos demonstrate improved motion realism and motion-identity consistency while maintaining high motion quality. Project page: https://vjwq.github.io/IAM △ Less

Submitted 27 April, 2026; originally announced April 2026.

Accelerating Regularized Attention Kernel Regression for Spectrum Cartography

Authors: Liping Tao, Chee Wei Tan

Abstract: Spectrum cartography reconstructs spatial radio fields from sparse and heterogeneous wireless measurements, underpinning many sensing and optimization tasks in wireless networks. Attention mechanisms have recently enabled adaptive measurement aggregation via attention kernel-based formulations. However, the resulting exponential kernels exhibit severe spectral imbalance, inducing large condition n… ▽ More Spectrum cartography reconstructs spatial radio fields from sparse and heterogeneous wireless measurements, underpinning many sensing and optimization tasks in wireless networks. Attention mechanisms have recently enabled adaptive measurement aggregation via attention kernel-based formulations. However, the resulting exponential kernels exhibit severe spectral imbalance, inducing large condition numbers that render standard iterative solvers ineffective for regularized attention kernel regression. This paper proposes a Learning-based Attention Kernel Regression (LAKER) algorithm for accelerating regularized attention kernel regression in spectrum cartography. The key idea is to learn a data-dependent preconditioner that captures the inverse spectral structure of the attention kernel system, directly reducing the condition number bottleneck. The preconditioner is obtained by solving a regularized maximum-likelihood estimation problem via a shrinkage-regularized convex--concave procedure, and is integrated with a preconditioned conjugate gradient solver for efficient optimization, whose solution is used for radio map reconstruction. Extensive experiments demonstrate that LAKER significantly reduces condition numbers by up to three orders of magnitude, accelerates convergence by over twenty-fold compared to baselines, and maintains high reconstruction accuracy, establishing learning-based preconditioning as an effective approach for attention kernel regression in spectrum cartography. △ Less

Submitted 27 April, 2026; originally announced April 2026.

Onboard Wind Estimation for Small UAVs Equipped with Low-Cost Sensors: An Aerodynamic Model-Integrated Filtering Approach

Authors: Bingchen Cheng, Tielin Ma, Jingcheng Fu, Lulu Tao, Tianhui Guo

Abstract: To enable autonomous wind estimation for energy-efficient flight in small unmanned aerial vehicles (UAVs), this study proposes a method that estimates flight states and wind using only the low-cost essential onboard sensors required for autonomous flight, without relying on additional wind measurement devices. The core of the method includes an Extended Kalman Filter (EKF) integrated with the aero… ▽ More To enable autonomous wind estimation for energy-efficient flight in small unmanned aerial vehicles (UAVs), this study proposes a method that estimates flight states and wind using only the low-cost essential onboard sensors required for autonomous flight, without relying on additional wind measurement devices. The core of the method includes an Extended Kalman Filter (EKF) integrated with the aerodynamic model and an Adaptive Moving Average Estimation (AMAE) technique, which improves the accuracy and smoothness of the wind estimation. Simulation results show that the approach efficiently estimates both steady and time-varying 3D wind vectors without requiring flow angle measurements. The impact of aerodynamic model accuracy on wind estimation errors is also analyzed to assess practical applicability. Flight tests validate the effectiveness of the method and its feasibility for real-time onboard computation. Additionally, uncertainties and error sources encountered during testing are systematically examined, providing a foundation for further refinement. △ Less

Submitted 22 April, 2026; originally announced April 2026.

CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference

Authors: Yulin Zou, Yan Chen, Wenyan Chen, JooYoung Park, Shivaraman Nitin, Luo Tao, Francisco Romero, Dmitrii Ustiugov

Abstract: Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalability. Prior systems reduce inference cost by exploiting temporal and spatial redundancy in video streams, but they target either the vision transformer (ViT) or the LLM with a limited view, leaving end-to-end opportunities untapped. Moreover, existing methods i… ▽ More Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalability. Prior systems reduce inference cost by exploiting temporal and spatial redundancy in video streams, but they target either the vision transformer (ViT) or the LLM with a limited view, leaving end-to-end opportunities untapped. Moreover, existing methods incur significant overhead to identify redundancy, either through offline profiling and training or costly online computation, making them ill-suited for dynamic real-time streams. We present CodecSight, a codec-guided streaming video analytics system, built on a key observation that video codecs already extract the temporal and spatial structure of each stream as a byproduct of compression. CodecSight treats this codec metadata as a low-cost runtime signal to unify optimization across video decoding, visual processing, and LLM prefilling, with transmission reduction as an inherent benefit of operating directly on compressed bitstreams. This drives codec-guided patch pruning before ViT encoding and selective key-value cache refresh during LLM prefilling, both of which are fully online and do not require offline training. Experiments show that CodecSight achieves an improvement in throughput of up to 3$\times$, and a reduction of up to 87% in GPU compute over state-of-the-art baselines, maintaining competitive accuracy with only 0$\sim$8% F1 drop. △ Less

Submitted 9 April, 2026; v1 submitted 7 April, 2026; originally announced April 2026.

Comments: 18 pages, 34 figures

Breakthrough the Suboptimal Stable Point in Value-Factorization-Based Multi-Agent Reinforcement Learning

Authors: Lesong Tao, Yifei Wang, Haodong Jing, Jingwen Fu, Miao Kang, Shitao Chen, Nanning Zheng

Abstract: Value factorization, a popular paradigm in MARL, faces significant theoretical and algorithmic bottlenecks: its tendency to converge to suboptimal solutions remains poorly understood and unsolved. Theoretically, existing analyses fail to explain this due to their primary focus on the optimal case. To bridge this gap, we introduce a novel theoretical concept: the stable point, which characterizes t… ▽ More Value factorization, a popular paradigm in MARL, faces significant theoretical and algorithmic bottlenecks: its tendency to converge to suboptimal solutions remains poorly understood and unsolved. Theoretically, existing analyses fail to explain this due to their primary focus on the optimal case. To bridge this gap, we introduce a novel theoretical concept: the stable point, which characterizes the potential convergence of value factorization in general cases. Through an analysis of stable point distributions in existing methods, we reveal that non-optimal stable points are the primary cause of poor performance. However, algorithmically, making the optimal action the unique stable point is nearly infeasible. In contrast, iteratively filtering suboptimal actions by rendering them unstable emerges as a more practical approach for global optimality. Inspired by this, we propose a novel Multi-Round Value Factorization (MRVF) framework. Specifically, by measuring a non-negative payoff increment relative to the previously selected action, MRVF transforms inferior actions into unstable points, thereby driving each iteration toward a stable point with a superior action. Experiments on challenging benchmarks, including predator-prey tasks and StarCraft II Multi-Agent Challenge (SMAC), validate our analysis of stable points and demonstrate the superiority of MRVF over state-of-the-art methods. △ Less

Submitted 6 April, 2026; originally announced April 2026.

Confidence Calibration under Ambiguous Ground Truth

Authors: Linwei Tao, Haoyang Luo, Minjing Dong, Chang Xu

Abstract: Confidence calibration assumes a unique ground-truth label per input, yet this assumption fails wherever annotators genuinely disagree. Post-hoc calibrators fitted on majority-voted labels, the standard single-label targets used in practice, can appear well-calibrated under conventional evaluation yet remain substantially miscalibrated against the underlying annotator distribution. We show that th… ▽ More Confidence calibration assumes a unique ground-truth label per input, yet this assumption fails wherever annotators genuinely disagree. Post-hoc calibrators fitted on majority-voted labels, the standard single-label targets used in practice, can appear well-calibrated under conventional evaluation yet remain substantially miscalibrated against the underlying annotator distribution. We show that this failure is structural: under simplifying assumptions, Temperature Scaling is biased toward temperatures that underestimate annotator uncertainty, with true-label miscalibration increasing monotonically with annotation entropy. To address this, we develop a family of ambiguity-aware post-hoc calibrators that optimise proper scoring rules against the full label distribution and require no model retraining. Our methods span progressively weaker annotation requirements: Dirichlet-Soft leverages the full annotator distribution and achieves the best overall calibration quality across settings; Monte Carlo Temperature Scaling with a single annotation per example (MCTS S=1) matches full-distribution calibration across all benchmarks, demonstrating that pre-aggregated label distributions are unnecessary; and Label-Smooth Temperature Scaling (LS-TS) operates with voted labels alone by constructing data-driven pseudo-soft targets from the model's own confidence. Experiments on four benchmarks with real multi-annotator distributions (CIFAR-10H, ChaosNLI) and clinically-informed synthetic annotations (ISIC~2019, DermaMNIST) show that Dirichlet-Soft reduces true-label ECE by 55-87% relative to Temperature Scaling, while LS-TS reduces ECE by 9-77% without any annotator data. △ Less

Submitted 24 March, 2026; originally announced March 2026.

JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization

Authors: Haolun Zheng, Yu He, Tailun Chen, Shuo Shao, Zhixuan Chu, Hongbin Zhou, Lan Tao, Zhan Qin, Kui Ren

Abstract: Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed safety filters. Existing jailbreak attacks either rely on proxy-loss optimization instead of the true end-to-end objective, or depend on large-scale and costly RL-trained generators. Motivated by these limitations, we pr… ▽ More Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed safety filters. Existing jailbreak attacks either rely on proxy-loss optimization instead of the true end-to-end objective, or depend on large-scale and costly RL-trained generators. Motivated by these limitations, we propose JANUS , a lightweight framework that formulates jailbreak as optimizing a structured prompt distribution under a black-box, end-to-end reward from the T2I system and its safety filters. JANUS replaces a high-capacity generator with a low-dimensional mixing policy over two semantically anchored prompt distributions, enabling efficient exploration while preserving the target semantics. On modern T2I models, we outperform state-of-the-art jailbreak methods, improving ASR-8 from 25.30% to 43.15% on Stable Diffusion 3.5 Large Turbo with consistently higher CLIP and NSFW scores. JANUS succeeds across both open-source and commercial models. These findings expose structural weaknesses in current T2I safety pipelines and motivate stronger, distribution-aware defenses. Warning: This paper contains model outputs that may be offensive. △ Less

Submitted 26 March, 2026; v1 submitted 22 March, 2026; originally announced March 2026.

Comments: This paper is accepted by the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026. 18 pages, 8 figures

Scalable Training of Mixture-of-Experts Models with Megatron Core

Authors: Zijie Yan, Hongxiao Bai, Xin Yao, Dennis Liu, Tong Liu, Hongbin Liu, Pingtian Li, Evan Wu, Shiqing Fan, Li Tao, Robin Zhang, Yuzhong Wang, Shifang Xu, Jack Chang, Xuwen Chen, Kunlun Li, Yan Bai, Gao Deng, Nan Zheng, Vijay Anand Korthikanti, Abhinav Khattar, Ethan He, Soham Govande, Sangkug Lym, Zhongbo Zhu , et al. (20 additional authors not shown)

Abstract: Scaling Mixture-of-Experts (MoE) training introduces systems challenges absent in dense models. Because each token activates only a subset of experts, this sparsity allows total parameters to grow much faster than per-token computation, creating coupled constraints across memory, communication, and computation. Optimizing one dimension often shifts pressure to another, demanding co-design across t… ▽ More Scaling Mixture-of-Experts (MoE) training introduces systems challenges absent in dense models. Because each token activates only a subset of experts, this sparsity allows total parameters to grow much faster than per-token computation, creating coupled constraints across memory, communication, and computation. Optimizing one dimension often shifts pressure to another, demanding co-design across the full system stack. We address these challenges for MoE training through integrated optimizations spanning memory (fine-grained recomputation, offloading, etc.), communication (optimized dispatchers, overlapping, etc.), and computation (Grouped GEMM, fusions, CUDA Graphs, etc.). The framework also provides Parallel Folding for flexible multi-dimensional parallelism, low-precision training support for FP8 and NVFP4, and efficient long-context training. On NVIDIA GB300 and GB200, it achieves 1,233/1,048 TFLOPS/GPU for DeepSeek-V3-685B and 974/919 TFLOPS/GPU for Qwen3-235B. As a performant, scalable, and production-ready open-source solution, it has been used across academia and industry for training MoE models ranging from billions to trillions of parameters on clusters scaling up to thousands of GPUs. This report explains how these techniques work, their trade-offs, and their interactions at the systems level, providing practical guidance for scaling MoE models with Megatron Core. △ Less

Submitted 10 March, 2026; v1 submitted 8 March, 2026; originally announced March 2026.

Comments: Technical Report. 88 pages. 42 figures

Capability Thresholds and Manufacturing Topology: How Embodied Intelligence Triggers Phase Transitions in Economic Geography

Authors: Xinmin Fang, Lingfeng Tao, Zhengxiong Li

Abstract: The fundamental topology of manufacturing has not undergone a paradigm-level transformation since Henry Ford's moving assembly line in 1913. Every major innovation of the past century, from the Toyota Production System to Industry 4.0, has optimized within the Fordist paradigm without altering its structural logic: centralized mega-factories, located near labor pools, producing at scale. We argue… ▽ More The fundamental topology of manufacturing has not undergone a paradigm-level transformation since Henry Ford's moving assembly line in 1913. Every major innovation of the past century, from the Toyota Production System to Industry 4.0, has optimized within the Fordist paradigm without altering its structural logic: centralized mega-factories, located near labor pools, producing at scale. We argue that embodied intelligence is poised to break this century-long stasis, not by making existing factories more efficient, but by triggering phase transitions in manufacturing economic geography itself. When embodied AI capabilities cross critical thresholds in dexterity, generalization, reliability, and tactile-vision fusion, the consequences extend far beyond cost reduction: they restructure where factories are built, how supply chains are organized, and what constitutes viable production scale. We formalize this by defining a Capability Space C = (d, g, r, t) and showing that the site-selection objective function undergoes topological reorganization when capability vectors cross critical surfaces. Through three pathways, weight inversion, batch collapse, and human-infrastructure decoupling, we show that embodied intelligence enables demand-proximal micro-manufacturing, eliminates "manufacturing deserts," and reverses geographic concentration driven by labor arbitrage. We further introduce Machine Climate Advantage: once human workers are removed, optimal factory locations are determined by machine-optimal conditions (low humidity, high irradiance, thermal stability), factors orthogonal to traditional siting logic, creating a production geography with no historical precedent. This paper establishes Embodied Intelligence Economics, the study of how physical AI capability thresholds reshape the spatial and structural logic of production. △ Less

Submitted 2 March, 2026; originally announced March 2026.

Real-Time Generative Policy via Langevin-Guided Flow Matching for Autonomous Driving

Authors: Tianze Zhu, Yinuo Wang, Wenjun Zou, Tianyi Zhang, Likun Wang, Letian Tao, Feihong Zhang, Yao Lyu, Shengbo Eben Li

Abstract: Reinforcement learning (RL) is a fundamental methodology in autonomous driving systems, where generative policies exhibit considerable potential by leveraging their ability to model complex distributions to enhance exploration. However, their inherent high inference latency severely impedes their deployment in real-time decision-making and control. To address this issue, we propose diffusion actor… ▽ More Reinforcement learning (RL) is a fundamental methodology in autonomous driving systems, where generative policies exhibit considerable potential by leveraging their ability to model complex distributions to enhance exploration. However, their inherent high inference latency severely impedes their deployment in real-time decision-making and control. To address this issue, we propose diffusion actor-critic with entropy regulator via flow matching (DACER-F) by introducing flow matching into online RL, enabling the generation of competitive actions in a single inference step. By leveraging Langevin dynamics and gradients of the Q-function, DACER-F dynamically optimizes actions from experience replay toward a target distribution that balances high Q-value information with exploratory behavior. The flow policy is then trained to efficiently learn a mapping from a simple prior distribution to this dynamic target. In complex multi-lane and intersection simulations, DACER-F outperforms baselines diffusion actor-critic with entropy regulator (DACER) and distributional soft actor-critic (DSAC), while maintaining an ultra-low inference latency. DACER-F further demonstrates its scalability on standard RL benchmark DeepMind Control Suite (DMC), achieving a score of 775.8 in the humanoid-stand task and surpassing prior methods. Collectively, these results establish DACER-F as a high-performance and computationally efficient RL algorithm. △ Less

Submitted 3 March, 2026; originally announced March 2026.

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens

Authors: Shiqi Liu, Zeyu He, Guojian Zhan, Letian Tao, Zhilong Zheng, Jiang Wu, Yinuo Wang, Yang Guan, Kehua Sheng, Bo Zhang, Keqiang Li, Jingliang Duan, Shengbo Eben Li

Abstract: Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In practice, they often suffer from late-stage performance collapse, leading to degraded reasoning quality and unstable training. We identify a key factor behind this ins… ▽ More Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In practice, they often suffer from late-stage performance collapse, leading to degraded reasoning quality and unstable training. We identify a key factor behind this instability: a small fraction of tokens, termed spurious tokens (around 0.01%), which contribute little to the reasoning outcome but receive disproportionately amplified gradient updates due to inheriting the full sequence-level reward. We present a unified framework for evaluating token-level optimization impacts across spurious risk, gradient norms, and entropy changes. Building on the analysis of token characteristics that severely disrupt optimization, we propose the Silencing Spurious Tokens (S2T) mechanism to efficiently suppress their gradient perturbations. Incorporating this mechanism into a group-based objective, we propose Spurious-Token-Aware Policy Optimization (STAPO), which promotes stable and effective large-scale model refinement. Across six mathematical reasoning benchmarks using Qwen 1.7B, 8B, and 14B base models, STAPO consistently demonstrates superior entropy stability and achieves an average performance improvement of 11.49% ($ρ_{\mathrm{T}}$=1.0, top-p=1.0) and 3.73% ($ρ_{\mathrm{T}}$=0.7, top-p=0.9) over GRPO, 20-Entropy, and JustRL. △ Less

Submitted 25 May, 2026; v1 submitted 17 February, 2026; originally announced February 2026.

Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets

Authors: Yuchen Yang, Wenze Lin, Enhao Huang, Zhixuan Chu, Hongbin Zhou, Lan Tao, Yiming Li, Zhan Qin, Kui Ren

Abstract: Large Language Models (LLMs) have seen remarkable advancements, achieving state-of-the-art results in diverse applications. Fine-tuning, an important step for adapting LLMs to specific downstream tasks, typically involves further training on corresponding datasets. However, a fundamental discrepancy exists between current fine-tuning datasets and the token-level optimization mechanism of LLMs: mos… ▽ More Large Language Models (LLMs) have seen remarkable advancements, achieving state-of-the-art results in diverse applications. Fine-tuning, an important step for adapting LLMs to specific downstream tasks, typically involves further training on corresponding datasets. However, a fundamental discrepancy exists between current fine-tuning datasets and the token-level optimization mechanism of LLMs: most datasets are designed at the sentence-level, which introduces token-level noise, causing negative influence to final performance. In this paper, we propose XTF, an explainable token-level noise filtering framework. XTF decomposes the complex and subtle contributions of token-level data to the fine-tuning process into three distinct and explicit attributes (reasoning importance, knowledge novelty, and task relevance), which can be assessed using scoring methods, and then masks the gradients of selected noisy tokens accordingly to optimize the performance of fine-tuned LLMs. We conduct extensive experiments on three representative downstream tasks (math, code and medicine) across 7 mainstream LLMs. The results demonstrate that XTF can significantly improve downstream performance by up to 13.7% compared to regular fine-tuning. Our work highlights the importance of token-level dataset optimization, and demonstrates the potential of strategies based on attribute decomposition for explaining complex training mechanisms. △ Less

Submitted 5 April, 2026; v1 submitted 16 February, 2026; originally announced February 2026.

Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation

Authors: Guojian Zhan, Letian Tao, Pengcheng Wang, Yixiao Wang, Yiheng Li, Yuxin Chen, Hongyang Li, Masayoshi Tomizuka, Shengbo Eben Li

Abstract: Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face a trade-off between expressiveness and computational burden, which is typically controlled by the number of flow steps. In this work,… ▽ More Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face a trade-off between expressiveness and computational burden, which is typically controlled by the number of flow steps. In this work, we propose mean velocity policy (MVP), a new generative policy function that models the mean velocity field to achieve the fastest one-step action generation. To ensure its high expressiveness, an instantaneous velocity constraint (IVC) is introduced on the mean velocity field during training. We theoretically prove that this design explicitly serves as a crucial boundary condition, thereby improving learning accuracy and enhancing policy expressiveness. Empirically, our MVP achieves state-of-the-art success rates across several challenging robotic manipulation tasks from Robomimic and OGBench. It also delivers substantial improvements in training and inference speed over existing flow-based policy baselines. △ Less

Submitted 7 March, 2026; v1 submitted 14 February, 2026; originally announced February 2026.

Comments: ICLR Oral Presentation

LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens

Authors: Zekun Li, Sizhe An, Chengcheng Tang, Chuan Guo, Ivan Shugurov, Linguang Zhang, Amy Zhao, Srinath Sridhar, Lingling Tao, Abhay Mittal

Abstract: Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored. Existing approaches often fine-tune large language models (LLMs) on paired motion-text data, which can result in catastrophic forgetting of linguistic capabilitie… ▽ More Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored. Existing approaches often fine-tune large language models (LLMs) on paired motion-text data, which can result in catastrophic forgetting of linguistic capabilities due to the limited scale of available text-motion pairs. Furthermore, prior methods typically convert motion into discrete representations via quantization to integrate with language models, introducing substantial jitter artifacts from discrete tokenization. To address these challenges, we propose LLaMo, a unified framework that extends pretrained LLMs through a modality-specific Mixture-of-Transformers (MoT) architecture. This design inherently preserves the language understanding of the base model while enabling scalable multimodal adaptation. We encode human motion into a causal continuous latent space and maintain the next-token prediction paradigm in the decoder-only backbone through a lightweight flow-matching head, allowing for streaming motion generation in real-time (>30 FPS). Leveraging the comprehensive language understanding of pretrained LLMs and large-scale motion-text pretraining, our experiments demonstrate that LLaMo achieves high-fidelity text-to-motion generation and motion-to-text captioning in general settings, especially zero-shot motion generation, marking a significant step towards a general unified motion-language large model. △ Less

Submitted 16 April, 2026; v1 submitted 12 February, 2026; originally announced February 2026.

Comments: Project page: https://kunkun0w0.github.io/project/LLaMo/

Talk2DM: Enabling Natural Language Querying and Commonsense Reasoning for Vehicle-Road-Cloud Integrated Dynamic Maps with Large Language Models

Authors: Lu Tao, Jinxuan Luo, Yousuke Watanabe, Zhengshu Zhou, Yuhuan Lu, Shen Ying, Pan Zhang, Fei Zhao, Hiroaki Takada

Abstract: Dynamic maps (DM) serve as the fundamental information infrastructure for vehicle-road-cloud (VRC) cooperative autonomous driving in China and Japan. By providing comprehensive traffic scene representations, DM overcome the limitations of standalone autonomous driving systems (ADS), such as physical occlusions. Although DM-enhanced ADS have been successfully deployed in real-world applications in… ▽ More Dynamic maps (DM) serve as the fundamental information infrastructure for vehicle-road-cloud (VRC) cooperative autonomous driving in China and Japan. By providing comprehensive traffic scene representations, DM overcome the limitations of standalone autonomous driving systems (ADS), such as physical occlusions. Although DM-enhanced ADS have been successfully deployed in real-world applications in Japan, existing DM systems still lack a natural-language-supported (NLS) human interface, which could substantially enhance human-DM interaction. To address this gap, this paper introduces VRCsim, a VRC cooperative perception (CP) simulation framework designed to generate streaming VRC-CP data. Based on VRCsim, we construct a question-answering data set, VRC-QA, focused on spatial querying and reasoning in mixed-traffic scenes. Building upon VRCsim and VRC-QA, we further propose Talk2DM, a plug-and-play module that extends VRC-DM systems with NLS querying and commonsense reasoning capabilities. Talk2DM is built upon a novel chain-of-prompt (CoP) mechanism that progressively integrates human-defined rules with the commonsense knowledge of large language models (LLMs). Experiments on VRC-QA show that Talk2DM can seamlessly switch across different LLMs while maintaining high NLS query accuracy, demonstrating strong generalization capability. Although larger models tend to achieve higher accuracy, they incur significant efficiency degradation. Our results reveal that Talk2DM, powered by Qwen3:8B, Gemma3:27B, and GPT-oss models, achieves over 93\% NLS query accuracy with an average response time of only 2-5 seconds, indicating strong practical potential. △ Less

Submitted 12 February, 2026; originally announced February 2026.

Comments: Submitted to IEEE TITS. Under review

Learning to Optimize by Differentiable Programming

Authors: Liping Tao, Xindi Tong, Chee Wei Tan

Abstract: Solving massive-scale optimization problems requires scalable first-order methods with low per-iteration cost. This tutorial highlights a shift in optimization: using differentiable programming not only to execute algorithms but to learn how to design them. Modern frameworks such as PyTorch, TensorFlow, and JAX enable this paradigm through efficient automatic differentiation. Embedding first-order… ▽ More Solving massive-scale optimization problems requires scalable first-order methods with low per-iteration cost. This tutorial highlights a shift in optimization: using differentiable programming not only to execute algorithms but to learn how to design them. Modern frameworks such as PyTorch, TensorFlow, and JAX enable this paradigm through efficient automatic differentiation. Embedding first-order methods within these systems allows end-to-end training that improves convergence and solution quality. Guided by Fenchel-Rockafellar duality, the tutorial demonstrates how duality-informed iterative schemes such as the alternating direction method of multipliers, and the primal-dual hybrid gradient can be learned and adapted through representative case studies. △ Less

Submitted 6 July, 2026; v1 submitted 23 January, 2026; originally announced January 2026.

Realistic Curriculum Reinforcement Learning for Autonomous and Sustainable Marine Vessel Navigation

Authors: Zhang Xiaocai, Xiao Zhe, Liang Maohan, Liu Tao, Li Haijiang, Zhang Wenbin

Abstract: Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on human experience, often lacking autonomy and emission awareness, and is prone to human errors that may compromise safety. In this paper, we propose a Curriculum… ▽ More Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on human experience, often lacking autonomy and emission awareness, and is prone to human errors that may compromise safety. In this paper, we propose a Curriculum Reinforcement Learning (CRL) framework integrated with a realistic, data-driven marine simulation environment and a machine learning-based fuel consumption prediction module. The simulation environment is constructed using real-world vessel movement data and enhanced with a Diffusion Model to simulate dynamic maritime conditions. Vessel fuel consumption is estimated using historical operational data and learning-based regression. The surrounding environment is represented as image-based inputs to capture spatial complexity. We design a lightweight, policy-based CRL agent with a comprehensive reward mechanism that considers safety, emissions, timeliness, and goal completion. This framework effectively handles complex tasks progressively while ensuring stable and efficient learning in continuous action spaces. We validate the proposed approach in a sea area of the Indian Ocean, demonstrating its efficacy in enabling sustainable and safe vessel navigation. △ Less

Submitted 15 January, 2026; originally announced January 2026.

Comments: Present in The 40th Annual AAAI Conference on Artificial Intelligence (AAAI-26)

PhysSFI-Net: Physics-informed Geometric Learning of Skeletal and Facial Interactions for Orthognathic Surgical Outcome Prediction

Authors: Jiahao Bao, Huazhen Liu, Yu Zhuang, Leran Tao, Xinyu Xu, Yongtao Shi, Mengjia Cheng, Yiming Wang, Congshuang Ku, Ting Zeng, Yilang Du, Siyi Chen, Shunyao Shen, Suncheng Xiang, Hongbo Yu

Abstract: Orthognathic surgery repositions jaw bones to restore occlusion and enhance facial aesthetics. Accurate simulation of postoperative facial morphology is essential for preoperative planning. This study aims to develop and validate a physics-informed geometric deep learning framework named PhysSFI-Net for precise prediction of soft tissue deformation following orthognathic surgery. The model integra… ▽ More Orthognathic surgery repositions jaw bones to restore occlusion and enhance facial aesthetics. Accurate simulation of postoperative facial morphology is essential for preoperative planning. This study aims to develop and validate a physics-informed geometric deep learning framework named PhysSFI-Net for precise prediction of soft tissue deformation following orthognathic surgery. The model integrates a hierarchical feature extraction module with attention mechanisms to capture skeletal-facial interactions, an LSTM-based sequential predictor for incremental deformation, and a biomechanics-inspired reconstruction module for high-resolution facial modeling. The model was trained on 135 patients and externally validated on an independent cohort of 33 patients. Model performance was assessed using point cloud shape error, surface deviation error and landmark error between predicted facial shapes with corresponding ground truths. Quantitative analysis demonstrated that PhysSFI-Net achieved a global shape error of 1.070 +/- 0.088 mm, a surface deviation error of 1.296 +/- 0.349 mm and a landmark error of 2.445 +/- 1.326 mm. Comparative experiments indicated that PhysSFI-Net outperformed the state-of-the-art method ACMT-Net and baseline models. External validation further confirmed its robustness with a global HD of 1.431 +/- 0.087 mm and consistently lower subregional and mesh-based errors. In conclusion, PhysSFI-Net enables interpretable, high-resolution prediction of postoperative facial morphology, showing strong potential for clinical application in orthognathic surgical planning. △ Less

Submitted 19 August, 2026; v1 submitted 5 January, 2026; originally announced January 2026.

Comments: 16 pages, 9 figures

Journal ref: Bao, J., Liu, H., Zhuang, Y. et al. PhysSFI-Net: physics-informed geometric learning of skeletal and facial interactions for orthognathic surgical outcome prediction. npj Digit. Med. (2026)

MMP-A*: Multimodal Perception Enhanced Incremental Heuristic Search on Path Planning

Authors: Minh Hieu Ha, Khanh Ly Ta, Hung Phan, Tung Doan, Tung Dao, Dao Tran, Huynh Thi Thanh Binh

Abstract: Autonomous path planning requires a synergy between global reasoning and geometric precision, especially in complex or cluttered environments. While classical A* is valued for its optimality, it incurs prohibitive computational and memory costs in large-scale scenarios. Recent attempts to mitigate these limitations by using Large Language Models for waypoint guidance remain insufficient, as they r… ▽ More Autonomous path planning requires a synergy between global reasoning and geometric precision, especially in complex or cluttered environments. While classical A* is valued for its optimality, it incurs prohibitive computational and memory costs in large-scale scenarios. Recent attempts to mitigate these limitations by using Large Language Models for waypoint guidance remain insufficient, as they rely only on text-based reasoning without spatial grounding. As a result, such models often produce incorrect waypoints in topologically complex environments with dead ends, and lack the perceptual capacity to interpret ambiguous physical boundaries. These inconsistencies lead to costly corrective expansions and undermine the intended computational efficiency. We introduce MMP-A*, a multimodal framework that integrates the spatial grounding capabilities of vision-language models with a novel adaptive decay mechanism. By anchoring high-level reasoning in physical geometry, the framework produces coherent waypoint guidance that addresses the limitations of text-only planners. The adaptive decay mechanism dynamically regulates the influence of uncertain waypoints within the heuristic, ensuring geometric validity while substantially reducing memory overhead. To evaluate robustness, we test the framework in challenging environments characterized by severe clutter and topological complexity. Experimental results show that MMP-A* achieves near-optimal trajectories with significantly reduced operational costs, demonstrating its potential as a perception-grounded and computationally efficient paradigm for autonomous navigation. △ Less

Submitted 22 January, 2026; v1 submitted 5 January, 2026; originally announced January 2026.

DS-HGCN: A Dual-Stream Hypergraph Convolutional Network for Predicting Student Engagement via Social Contagion

Authors: Ziyang Fan, Li Tao, Yi Wang, Jingwei Qu, Ying Wang, Fei Jiang

Abstract: Student engagement is a critical factor influencing academic success and learning outcomes. Accurately predicting student engagement is essential for optimizing teaching strategies and providing personalized interventions. However, most approaches focus on single-dimensional feature analysis and assessing engagement based on individual student factors. In this work, we propose a dual-stream multi-… ▽ More Student engagement is a critical factor influencing academic success and learning outcomes. Accurately predicting student engagement is essential for optimizing teaching strategies and providing personalized interventions. However, most approaches focus on single-dimensional feature analysis and assessing engagement based on individual student factors. In this work, we propose a dual-stream multi-feature fusion model based on hypergraph convolutional networks (DS-HGCN), incorporating social contagion of student engagement. DS-HGCN enables accurate prediction of student engagement states by modeling multi-dimensional features and their propagation mechanisms between students. The framework constructs a hypergraph structure to encode engagement contagion among students and captures the emotional and behavioral differences and commonalities by multi-frequency signals. Furthermore, we introduce a hypergraph attention mechanism to dynamically weigh the influence of each student, accounting for individual differences in the propagation process. Extensive experiments on public benchmark datasets demonstrate that our proposed method achieves superior performance and significantly outperforms existing state-of-the-art approaches. △ Less

Submitted 23 December, 2025; originally announced December 2025.

Comments: 14pages,Accepted by MMM2026

AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition

Authors: Zichuan Lin, Yicheng Liu, Yang Yang, Lvfang Tao, Deheng Ye

Abstract: Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches reduce visual tokens through fixed-ratio compression, they operate passively and lack the ability to adapt to varying task requirements. This motivates a fundame… ▽ More Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches reduce visual tokens through fixed-ratio compression, they operate passively and lack the ability to adapt to varying task requirements. This motivates a fundamental question: Can VLMs autonomously determine the minimum number of visual tokens required for each sample? Inspired by human active vision mechanisms, we introduce AdaptVision, an efficient VLM paradigm that enables adaptive visual token acquisition through a coarse-to-fine approach. Our model initially processes compressed visual tokens from low-resolution images and selectively acquires additional visual information by invoking a bounding box tool to crop key regions when necessary. We train AdaptVision using a reinforcement learning framework that carefully balances accuracy and efficiency. Central to our approach is Decoupled Turn Policy Optimization (DTPO), which decouples the learning objective into two components: (1) tool learning, which optimizes correct tool utilization, and (2) accuracy improvement, which refines the generated responses to improve answer correctness. Based on this formulation, we further decouple advantage estimation by computing separate advantages for tokens associated with each objective. This formulation enables more effective optimization for AdaptVision compared to vanilla GRPO. Comprehensive experiments across multiple VQA benchmarks demonstrate that AdaptVision achieves superior performance while consuming substantially fewer visual tokens than state-of-the-art efficient VLM methods. △ Less

Submitted 20 March, 2026; v1 submitted 3 December, 2025; originally announced December 2025.

Comments: Accepted by CVPR 2026. Code and models are available at https://github.com/AdaptVision/AdaptVision

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport

Authors: Zecheng Pan, Zhikang Chen, Ding Li, Min Zhang, Sen Cui, Hongshuo Jin, Luqi Tao, Yi Yang, Deheng Ye, Yu Zhang, Tingting Zhu, Tianling Ren

Abstract: Merging models fine-tuned for different tasks into a single unified model has become an increasingly important direction for building versatile, efficient multi-task systems. Existing approaches predominantly rely on parameter interpolation in weight space, which we show introduces significant distribution shift in the feature space and undermines task-specific knowledge. In this paper, we propose… ▽ More Merging models fine-tuned for different tasks into a single unified model has become an increasingly important direction for building versatile, efficient multi-task systems. Existing approaches predominantly rely on parameter interpolation in weight space, which we show introduces significant distribution shift in the feature space and undermines task-specific knowledge. In this paper, we propose OTMF (Optimal Transport-based Masked Fusion), a novel model merging framework rooted in optimal transport theory to address the distribution shift that arises from naive parameter interpolation. Instead of directly aggregating features or weights, OTMF aligns the semantic geometry of task-specific models by discovering common masks applied to task vectors through optimal transport plans. These masks selectively extract transferable and task-agnostic components while preserving the unique structural identities of each task. To ensure scalability in real-world settings, OTMF further supports a continual fusion paradigm that incrementally integrates each new task vector without revisiting previous ones, maintaining a bounded memory footprint and enabling efficient fusion across a growing number of tasks. We conduct comprehensive experiments on multiple vision and language benchmarks, and results show that OTMF achieves state-of-the-art performance in terms of both accuracy and efficiency. These findings highlight the practical and theoretical value of our approach to model merging. △ Less

Submitted 24 November, 2025; originally announced November 2025.

Referring Camouflaged Object Detection With Multi-Context Overlapped Windows Cross-Attention

Authors: Yu Wen, Shuyong Gao, Shuping Zhang, Miao Huang, Lili Tao, Han Yang, Haozhe Xing, Lihe Zhang, Boxue Hou

Abstract: Referring camouflaged object detection (Ref-COD) aims to identify hidden objects by incorporating reference information such as images and text descriptions. Previous research has transformed reference images with salient objects into one-dimensional prompts, yielding significant results. We explore ways to enhance performance through multi-context fusion of rich salient image features and camoufl… ▽ More Referring camouflaged object detection (Ref-COD) aims to identify hidden objects by incorporating reference information such as images and text descriptions. Previous research has transformed reference images with salient objects into one-dimensional prompts, yielding significant results. We explore ways to enhance performance through multi-context fusion of rich salient image features and camouflaged object features. Therefore, we propose RFMNet, which utilizes features from multiple encoding stages of the reference salient images and performs interactive fusion with the camouflage features at the corresponding encoding stages. Given that the features in salient object images contain abundant object-related detail information, performing feature fusion within local areas is more beneficial for detecting camouflaged objects. Therefore, we propose an Overlapped Windows Cross-attention mechanism to enable the model to focus more attention on the local information matching based on reference features. Besides, we propose the Referring Feature Aggregation (RFA) module to decode and segment the camouflaged objects progressively. Extensive experiments on the Ref-COD benchmark demonstrate that our method achieves state-of-the-art performance. △ Less

Submitted 17 November, 2025; originally announced November 2025.

Comments: 12 pages, 7figures, This work is supported by National Nature Science Foundation of China (Grant No. 62203291)

End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection

Authors: Yu Cui, Yujian Zhang, Lina Tao, Yang Li, Xinyu Yi, Zhibin Li

Abstract: Achieving human-like dexterous manipulation remains a major challenge for general-purpose robots. While Vision-Language-Action (VLA) models show potential in learning skills from demonstrations, their scalability is limited by scarce high-quality training data. Existing data collection methods face inherent constraints: manual teleoperation overloads human operators, while automated planning often… ▽ More Achieving human-like dexterous manipulation remains a major challenge for general-purpose robots. While Vision-Language-Action (VLA) models show potential in learning skills from demonstrations, their scalability is limited by scarce high-quality training data. Existing data collection methods face inherent constraints: manual teleoperation overloads human operators, while automated planning often produces unnatural motions. We propose a Shared Autonomy framework that divides control between macro and micro motions. A human operator guides the robot's arm pose through intuitive VR teleoperation, while an autonomous DexGrasp-VLA policy handles fine-grained hand control using real-time tactile and visual feedback. This division significantly reduces cognitive load and enables efficient collection of high-quality coordinated arm-hand demonstrations. Using this data, we train an end-to-end VLA policy enhanced with our novel Arm-Hand Feature Enhancement module, which captures both distinct and shared representations of macro and micro movements for more natural coordination. Our Corrective Teleoperation system enables continuous policy improvement through human-in-the-loop failure recovery. Experiments demonstrate that our framework generates high-quality data with minimal manpower and achieves a 90% success rate across diverse objects, including unseen instances. Comprehensive evaluations validate the system's effectiveness in developing dexterous manipulation capabilities. △ Less

Submitted 13 December, 2025; v1 submitted 31 October, 2025; originally announced November 2025.

OpsAgent: An Evolving Multi-agent System for Incident Management in Microservices

Authors: Yu Luo, Jiamin Jiang, Jingfei Feng, Lei Tao, Qingliang Zhang, Xidao Wen, Yongqian Sun, Shenglin Zhang, Dan Pei

Abstract: Incident management (IM) is central to the reliability of large-scale microservice systems. Yet manual IM, where on-call engineers examine metrics, logs, and traces is labor-intensive and error-prone in the face of massive and heterogeneous observability data. Existing automated IM approaches often struggle to generalize across systems, provide limited interpretability, and incur high deployment c… ▽ More Incident management (IM) is central to the reliability of large-scale microservice systems. Yet manual IM, where on-call engineers examine metrics, logs, and traces is labor-intensive and error-prone in the face of massive and heterogeneous observability data. Existing automated IM approaches often struggle to generalize across systems, provide limited interpretability, and incur high deployment costs, which hinders adoption in practice. In this paper, we present OpsAgent, a lightweight, self-evolving multi-agent system for IM that employs a training-free data processor to convert heterogeneous observability data into structured textual descriptions, along with a multi-agent collaboration framework that makes diagnostic inference transparent and auditable. To support continual capability growth, OpsAgent also introduces a dual self-evolution mechanism that integrates internal model updates with external experience accumulation, thereby closing the deployment loop. Comprehensive experiments on the OPENRCA benchmark demonstrate state-of-the-art performance and show that OpsAgent is generalizable, interpretable, cost-efficient, and self-evolving, making it a practically deployable and sustainable solution for long-term operation in real-world microservice systems. Notably, its deployment in Lenovo's production environment further validates its effectiveness in real-world industrial settings. △ Less

Submitted 12 May, 2026; v1 submitted 28 October, 2025; originally announced October 2025.

Aligning Multilingual News for Stock Return Prediction

Authors: Yuntao Wu, Lynn Tao, Ing-Haw Cheng, Charles Martineau, Yoshio Nozawa, John Hull, Andreas Veneris

Abstract: News spreads rapidly across languages and regions, but translations may lose subtle nuances. We propose a method to align sentences in multilingual news articles using optimal transport, identifying semantically similar content across languages. We apply this method to align more than 140,000 pairs of Bloomberg English and Japanese news articles covering around 3500 stocks in Tokyo exchange over 2… ▽ More News spreads rapidly across languages and regions, but translations may lose subtle nuances. We propose a method to align sentences in multilingual news articles using optimal transport, identifying semantically similar content across languages. We apply this method to align more than 140,000 pairs of Bloomberg English and Japanese news articles covering around 3500 stocks in Tokyo exchange over 2012-2024. Aligned sentences are sparser, more interpretable, and exhibit higher semantic similarity. Return scores constructed from aligned sentences show stronger correlations with realized stock returns, and long-short trading strategies based on these alignments achieve 10\% higher Sharpe ratios than analyzing the full text sample. △ Less

Submitted 21 October, 2025; originally announced October 2025.

Comments: 6 pages, 4 tables, 2 figures, AI for Finance Symposium'25 Workshop at ICAIF'25

ACM Class: J.4; I.2.7

Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

Authors: Leitian Tao, Ilia Kulikov, Swarnadeep Saha, Tianlu Wang, Jing Xu, Sharon Li, Jason E Weston, Ping Yu

Abstract: Post-training for reasoning of large language models (LLMs) increasingly relies on verifiable rewards: deterministic checkers that provide 0-1 correctness signals. While reliable, such binary feedback is brittle--many tasks admit partially correct or alternative answers that verifiers under-credit, and the resulting all-or-nothing supervision limits learning. Reward models offer richer, continuous… ▽ More Post-training for reasoning of large language models (LLMs) increasingly relies on verifiable rewards: deterministic checkers that provide 0-1 correctness signals. While reliable, such binary feedback is brittle--many tasks admit partially correct or alternative answers that verifiers under-credit, and the resulting all-or-nothing supervision limits learning. Reward models offer richer, continuous feedback, which can serve as a complementary supervisory signal to verifiers. We introduce HERO (Hybrid Ensemble Reward Optimization), a reinforcement learning framework that integrates verifier signals with reward-model scores in a structured way. HERO employs stratified normalization to bound reward-model scores within verifier-defined groups, preserving correctness while refining quality distinctions, and variance-aware weighting to emphasize challenging prompts where dense signals matter most. Across diverse mathematical reasoning benchmarks, HERO consistently outperforms RM-only and verifier-only baselines, with strong gains on both verifiable and hard-to-verify tasks. Our results show that hybrid reward design retains the stability of verifiers while leveraging the nuance of reward models to advance reasoning. △ Less

Submitted 17 October, 2025; v1 submitted 8 October, 2025; originally announced October 2025.

Comments: 21 pages

RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization

Authors: Zhaoning Yu, Will Su, Leitian Tao, Haozhu Wang, Aashu Singh, Hanchao Yu, Jianyu Wang, Hongyang Gao, Weizhe Yuan, Jason Weston, Ping Yu, Jing Xu

Abstract: Reinforcement learning with human-annotated data has boosted chain-of-thought reasoning in large reasoning models, but these gains come at high costs in labeled data while faltering on harder tasks. A natural next step is experience-driven learning, where models improve without curated labels by adapting to unlabeled data. We introduce RESTRAIN (REinforcement learning with Self-restraint), a self-… ▽ More Reinforcement learning with human-annotated data has boosted chain-of-thought reasoning in large reasoning models, but these gains come at high costs in labeled data while faltering on harder tasks. A natural next step is experience-driven learning, where models improve without curated labels by adapting to unlabeled data. We introduce RESTRAIN (REinforcement learning with Self-restraint), a self-penalizing RL framework that converts the absence of gold labels into a useful learning signal. Instead of overcommitting to spurious majority votes, RESTRAIN exploits signals from the model's entire answer distribution: penalizing overconfident rollouts and low-consistency examples while preserving promising reasoning chains. The self-penalization mechanism integrates seamlessly into policy optimization methods such as GRPO, enabling continual self-improvement without supervision. On challenging reasoning benchmarks, RESTRAIN delivers large gains using only unlabeled data. With Qwen3-4B-Base and OctoThinker Hybrid-8B-Base, it improves Pass@1 by up to +140.7 percent on AIME25, +36.2 percent on MMLU_STEM, and +19.6 percent on GPQA-Diamond, nearly matching gold-label training while using no gold labels. These results demonstrate that RESTRAIN establishes a scalable path toward stronger reasoning without gold labels. △ Less

Submitted 2 October, 2025; originally announced October 2025.

Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis

Authors: Leitian Tao, Xuefeng Du, Sharon Li

Abstract: Reward modeling, crucial for aligning large language models (LLMs) with human preferences, is often bottlenecked by the high cost of preference data. Existing textual data synthesis methods are computationally expensive. We propose a novel framework LENS for synthesizing preference data directly in the LLM's latent embedding space. Our method employs a Variational Autoencoder (VAE) to learn a stru… ▽ More Reward modeling, crucial for aligning large language models (LLMs) with human preferences, is often bottlenecked by the high cost of preference data. Existing textual data synthesis methods are computationally expensive. We propose a novel framework LENS for synthesizing preference data directly in the LLM's latent embedding space. Our method employs a Variational Autoencoder (VAE) to learn a structured latent representation of response embeddings. By performing controlled perturbations in this latent space and decoding back to the embedding space, we efficiently generate diverse, semantically consistent synthetic preference pairs, bypassing costly text generation and annotation. We provide theoretical guarantees that our synthesized pairs approximately preserve original preference ordering and improve reward model generalization. Empirically, our latent-space synthesis significantly outperforms text-based augmentation on standard benchmarks, achieving superior results while being 18x faster in generation and using a 16,000x smaller model. Our work offers a scalable and effective alternative for enhancing reward modeling through efficient data augmentation. Code is publicly available at https://github.com/deeplearning-wisc/lens △ Less

Submitted 14 October, 2025; v1 submitted 30 September, 2025; originally announced September 2025.

Comments: Accepted by NeurIPS 2025

The Era of Real-World Human Interaction: RL from User Conversations

Authors: Chuanyang Jin, Jing Xu, Bo Liu, Leitian Tao, Olga Golovneva, Tianmin Shu, Wenting Zhao, Xian Li, Jason Weston

Abstract: We posit that to achieve continual model improvement and multifaceted alignment, future models must learn from natural human interaction. Current conversational models are aligned using pre-annotated, expert-generated human feedback. In this work, we introduce Reinforcement Learning from Human Interaction (RLHI), a paradigm that learns directly from in-the-wild user conversations. We develop two c… ▽ More We posit that to achieve continual model improvement and multifaceted alignment, future models must learn from natural human interaction. Current conversational models are aligned using pre-annotated, expert-generated human feedback. In this work, we introduce Reinforcement Learning from Human Interaction (RLHI), a paradigm that learns directly from in-the-wild user conversations. We develop two complementary methods: (1) RLHI with User-Guided Rewrites, which revises unsatisfactory model outputs based on users' natural-language follow-up responses, (2) RLHI with User-Based Rewards, which learns via a reward model conditioned on knowledge of the user's long-term interaction history (termed persona). Together, these methods link long-term user personas to turn-level preferences via persona-conditioned preference optimization. Trained on conversations derived from WildChat, both RLHI variants outperform strong baselines in personalization and instruction-following, and similar feedback enhances performance on reasoning benchmarks. These results suggest organic human interaction offers scalable, effective supervision for personalized alignment. △ Less

Submitted 29 September, 2025; originally announced September 2025.

Can Large Language Models Express Uncertainty Like Human?

Authors: Linwei Tao, Yi-Fan Yeh, Bo Kai, Minjing Dong, Tao Huang, Tom A. Lamb, Jialin Yu, Philip H. S. Torr, Chang Xu

Abstract: Large language models (LLMs) are increasingly used in high-stakes settings, where overconfident responses can mislead users. Reliable confidence estimation has been shown to enhance trust and task accuracy. Yet existing methods face practical barriers: logits are often hidden, multi-sampling is computationally expensive, and verbalized numerical uncertainty (e.g., giving a 0-100 score) deviates fr… ▽ More Large language models (LLMs) are increasingly used in high-stakes settings, where overconfident responses can mislead users. Reliable confidence estimation has been shown to enhance trust and task accuracy. Yet existing methods face practical barriers: logits are often hidden, multi-sampling is computationally expensive, and verbalized numerical uncertainty (e.g., giving a 0-100 score) deviates from natural communication. We revisit linguistic confidence (LC), where models express uncertainty through hedging language (e.g., probably, might), offering a lightweight and human-centered alternative. To advance this direction, we (1) release the first diverse, large-scale dataset of hedging expressions with human-annotated confidence scores, and (2) propose a lightweight mapper that converts hedges into confidence scores at near-zero cost. Building on these resources, we (3) conduct the first systematic study of LC across modern LLMs and QA benchmarks, revealing that while most LLMs underperform in expressing reliable LC, carefully designed prompting achieves competitive calibration and discriminability. Finally, we (4) introduce a fine-tuning framework that further improves LC reliability. Taken together, our work positions linguistic confidence as a scalable, efficient, and human-aligned approach to LLM uncertainty estimation, and calls for deeper exploration of this promising yet underexplored direction. △ Less

Submitted 28 September, 2025; originally announced September 2025.

Comments: 10 pages

MRN: Harnessing 2D Vision Foundation Models for Diagnosing Parkinson's Disease with Limited 3D MR Data

Authors: Ding Shaodong, Liu Ziyang, Zhou Yijun, Liu Tao

Abstract: The automatic diagnosis of Parkinson's disease is in high clinical demand due to its prevalence and the importance of targeted treatment. Current clinical practice often relies on diagnostic biomarkers in QSM and NM-MRI images. However, the lack of large, high-quality datasets makes training diagnostic models from scratch prone to overfitting. Adapting pre-trained 3D medical models is also challen… ▽ More The automatic diagnosis of Parkinson's disease is in high clinical demand due to its prevalence and the importance of targeted treatment. Current clinical practice often relies on diagnostic biomarkers in QSM and NM-MRI images. However, the lack of large, high-quality datasets makes training diagnostic models from scratch prone to overfitting. Adapting pre-trained 3D medical models is also challenging, as the diversity of medical imaging leads to mismatches in voxel spacing and modality between pre-training and fine-tuning data. In this paper, we address these challenges by leveraging 2D vision foundation models (VFMs). Specifically, we crop multiple key ROIs from NM and QSM images, process each ROI through separate branches to compress the ROI into a token, and then combine these tokens into a unified patient representation for classification. Within each branch, we use 2D VFMs to encode axial slices of the 3D ROI volume and fuse them into the ROI token, guided by an auxiliary segmentation head that steers the feature extraction toward specific brain nuclei. Additionally, we introduce multi-ROI supervised contrastive learning, which improves diagnostic performance by pulling together representations of patients from the same class while pushing away those from different classes. Our approach achieved first place in the MICCAI 2025 PDCADxFoundation challenge, with an accuracy of 86.0% trained on a dataset of only 300 labeled QSM and NM-MRI scans, outperforming the second-place method by 5.5%.These results highlight the potential of 2D VFMs for clinical analysis of 3D MR images. △ Less

Submitted 22 September, 2025; originally announced September 2025.

Comments: First-place solution of the classification track for MICCAI'2025 PDCADxFoundation Challenge

PHM-Bench: A Domain-Specific Benchmarking Framework for Systematic Evaluation of Large Models in Prognostics and Health Management

Authors: Puyu Yang, Laifa Tao, Zijian Huang, Haifei Liu, Wenyan Cao, Hao Ji, Jianan Qiu, Qixuan Huang, Xuanyuan Su, Yuhang Xie, Jun Zhang, Shangyu Li, Chen Lu, Zhixuan Lian

Abstract: With the rapid advancement of generative artificial intelligence, large language models (LLMs) are increasingly adopted in industrial domains, offering new opportunities for Prognostics and Health Management (PHM). These models help address challenges such as high development costs, long deployment cycles, and limited generalizability. However, despite the growing synergy between PHM and LLMs, exi… ▽ More With the rapid advancement of generative artificial intelligence, large language models (LLMs) are increasingly adopted in industrial domains, offering new opportunities for Prognostics and Health Management (PHM). These models help address challenges such as high development costs, long deployment cycles, and limited generalizability. However, despite the growing synergy between PHM and LLMs, existing evaluation methodologies often fall short in structural completeness, dimensional comprehensiveness, and evaluation granularity. This hampers the in-depth integration of LLMs into the PHM domain. To address these limitations, this study proposes PHM-Bench, a novel three-dimensional evaluation framework for PHM-oriented large models. Grounded in the triadic structure of fundamental capability, core task, and entire lifecycle, PHM-Bench is tailored to the unique demands of PHM system engineering. It defines multi-level evaluation metrics spanning knowledge comprehension, algorithmic generation, and task optimization. These metrics align with typical PHM tasks, including condition monitoring, fault diagnosis, RUL prediction, and maintenance decision-making. Utilizing both curated case sets and publicly available industrial datasets, our study enables multi-dimensional evaluation of general-purpose and domain-specific models across diverse PHM tasks. PHM-Bench establishes a methodological foundation for large-scale assessment of LLMs in PHM and offers a critical benchmark to guide the transition from general-purpose to PHM-specialized models. △ Less

Submitted 4 August, 2025; originally announced August 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

Optimization of Low-Latency Spiking Neural Networks Utilizing Historical Dynamics of Refractory Periods

Authors: Liying Tao, Zonglin Yang, Delong Shang

Abstract: The refractory period controls neuron spike firing rate, crucial for network stability and noise resistance. With advancements in spiking neural network (SNN) training methods, low-latency SNN applications have expanded. In low-latency SNNs, shorter simulation steps render traditional refractory mechanisms, which rely on empirical distributions or spike firing rates, less effective. However, omitt… ▽ More The refractory period controls neuron spike firing rate, crucial for network stability and noise resistance. With advancements in spiking neural network (SNN) training methods, low-latency SNN applications have expanded. In low-latency SNNs, shorter simulation steps render traditional refractory mechanisms, which rely on empirical distributions or spike firing rates, less effective. However, omitting the refractory period amplifies the risk of neuron over-activation and reduces the system's robustness to noise. To address this challenge, we propose a historical dynamic refractory period (HDRP) model that leverages membrane potential derivative with historical refractory periods to estimate an initial refractory period and dynamically adjust its duration. Additionally, we propose a threshold-dependent refractory kernel to mitigate excessive neuron state accumulation. Our approach retains the binary characteristics of SNNs while enhancing both noise resistance and overall performance. Experimental results show that HDRP-SNN significantly reduces redundant spikes compared to traditional SNNs, and achieves state-of-the-art (SOTA) accuracy both on static datasets and neuromorphic datasets. Moreover, HDRP-SNN outperforms artificial neural networks (ANNs) and traditional SNNs in noise resistance, highlighting the crucial role of the HDRP mechanism in enhancing the performance of low-latency SNNs. △ Less

Submitted 30 June, 2025; originally announced July 2025.

UVLM: Benchmarking Video Language Model for Underwater World Understanding

Authors: Xizhe Xue, Yang Zhou, Dawei Yan, Lijie Tao, Junjie Li, Ying Li, Haokui Zhang, Rong Xiao

Abstract: Recently, the remarkable success of large language models (LLMs) has achieved a profound impact on the field of artificial intelligence. Numerous advanced works based on LLMs have been proposed and applied in various scenarios. Among them, video language models (VidLMs) are particularly widely used. However, existing works primarily focus on terrestrial scenarios, overlooking the highly demanding… ▽ More Recently, the remarkable success of large language models (LLMs) has achieved a profound impact on the field of artificial intelligence. Numerous advanced works based on LLMs have been proposed and applied in various scenarios. Among them, video language models (VidLMs) are particularly widely used. However, existing works primarily focus on terrestrial scenarios, overlooking the highly demanding application needs of underwater observation. To overcome this gap, we introduce UVLM, an under water observation benchmark which is build through a collaborative approach combining human expertise and AI models. To ensure data quality, we have conducted in-depth considerations from multiple perspectives. First, to address the unique challenges of underwater environments, we selected videos that represent typical underwater challenges including light variations, water turbidity, and diverse viewing angles to construct the dataset. Second, to ensure data diversity, the dataset covers a wide range of frame rates, resolutions, 419 classes of marine animals, and various static plants and terrains. Next, for task diversity, we adopted a structured design where observation targets are categorized into two major classes: biological and environmental. Each category includes content observation and change/action observation, totaling 20 distinct task types. Finally, we designed several challenging evaluation metrics to enable quantitative comparison and analysis of different methods. Experiments on two representative VidLMs demonstrate that fine-tuning VidLMs on UVLM significantly improves underwater world understanding while also showing potential for slight improvements on existing in-air VidLM benchmarks, such as VideoMME and Perception text. The dataset and prompt engineering will be released publicly. △ Less

Submitted 18 November, 2025; v1 submitted 3 July, 2025; originally announced July 2025.

Comments: 18 pages, 10 figures, 7 tables. Accepted to the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), 2026