Sparse
-
ReLiveGym: Evaluating Long-Lived Agents over Weeks of Replayed Reality
2026-09-30 20:59:33Xisen Jin, Jingheng Li, Zhenglun Chen, Junyi Du, Xiang RenAbstract
As large language model (LLM) agents become widely adopted, they are increasingly deployed for tasks that require persistent monitoring or recurring actions (e.g., market analysis). These agents are expected to operate unattended for days or weeks, act at the right timing, and adapt to the dynamic environment over time. These challenges are not fully captured in the existing long-horizon agent work, as they often consider a static environment that is not temporally changing. We introduce ReLiveGym, a diagnostic evaluation environment of long-lived tasks in which agents act sparsely over simulated weeks of chronologically replayed real-world news, market, and social-media streams. The tasks span diverse levels of time sensitivity, reasoning intensity, and recurrence. Across eight base language models, we investigate how model choice and harness design affect agent performance on such long-lived tasks. Our results show that how agents determine when to act arises as an important harness-design axis for long-lived tasks; and that the optimal design varies across tasks and sometimes model choices as well. We also evaluate how continuous learning from hindsight feedback affects performance and addresses failure modes observed in these long-lived tasks. These findings indicate model choice, action timing mechanism, and use of feedback as important considerations in the design of long-lived agents. Code: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.00710
PDF
-
Agent Evaluation Reliability: More Tasks Won't Fix An Agent Leaderboard
2026-09-30 19:52:09Michael Hardy, Ruhana Azam, Anka Reuel, Mykel Kochenderfer, Sanmi KoyejoAbstract
Agent evaluations are increasingly used to compare LLMs and inform deployment decisions, yet ranks can reflect not only the model but also the effects of the evaluation conditions such as the scaffolds or tasks. This makes reliability claim-dependent: an evaluation that reliably ranks deployed systems may not reliably rank underlying models. We ask which conclusions current agent evaluations reliably support and what additional evaluation would improve them. We develop a Bayesian variance-decomposition framework for sparse, imbalanced agent leaderboards and apply it to 22 benchmarks from the Holistic Agent Leaderboard and Harbor Index. The framework separates signal, performance differences relevant to the intended claim, from noise, irrelevant variation that can still change rankings. We find: (1) Reliability depends on the measurement goal. Fixed model-scaffold systems are ranked reliably (0.935-0.994), while underlying-model reliability is substantially lower (0.148-0.841). (2) Scaffold choice can change conclusions. Inter-scaffold reliability measures whether scaffolds preserve model rankings, showing that scaffold effects vary substantially across evaluations. (3) More tasks cannot resolve all uncertainty. Even infinitely many similarly constructed tasks improve model-ranking reliability of a benchmark by at most 0.097 when uncertainty is dominated by limited scaffold coverage. (4) Pooling diverse benchmarks can improve cross-task rankings at lower cost. For rankings across diverse agentic tasks, pooling benchmarks raises projected reliability from 0.44 to 0.75 at the same task budget and can reduce projected cost by up to 83\%. Evaluation design should follow the intended claim: identify what a score or ranking should mean, diagnose what limits its reliability, and spend evaluation budget on the sources of uncertainty that matter.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00651
PDF
-
FORTE: Adaptive Scoring and Exact Keyframe Selection for Long-Video Question Answering
2026-09-30 18:45:18Haifeng Huang, Biyin Xu, Chunsheng Xin, Yang LiAbstract
Query-aware keyframe selection enables multimodal large language models (MLLMs) to process long videos using only a small set of question-relevant frames. Existing score-based methods, however, typically search within a fixed, uniformly sampled candidate pool, preventing evidence outside this pool from ever being selected. Given a limited relevance-scoring budget, the key challenge is to allocate evaluations adaptively to promising frames while continuing to explore underrepresented temporal regions. We introduce FORTE, a training-free framework that addresses this challenge through two stages: adaptive relevance scoring and global keyframe optimization. Starting from sparse, uniformly distributed observations, our efficient Gaussian-process relevance predictor estimates relevance for unscored frames, exploiting temporal locality and the approximately banded kernel structure to reduce the core computation from cubic to linear time in the number of frames for fixed bandwidth. The scoring stage then selects which frames to score next by balancing predicted relevance with temporal coverage, prioritizing promising regions while also exploring less-represented parts of the video. The optimization stage selects the final keyframes by maximizing an objective that jointly captures measured relevance and temporal coverage. We derive an exact algorithm that leverages the logarithmic coverage structure to identify the optimal subset of the scored candidate pool in time linear in the pool size, for a fixed final-frame budget. Experiments on four long-video question-answering benchmarks show that FORTE achieves the highest observed mean accuracy among the compared selectors under every tested scoring budget. Further evaluations demonstrate its consistent effectiveness across different relevance scorers and downstream MLLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00573
PDF
-
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents
2026-09-30 17:40:09Yong Du, Tongbo Chen, Zhengxi Lu, Yizhou Liu, Bofan Chen, Tao Jiang, Wenhao Xu, Yongliang ShenAbstract
Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards, which provide no supervision for intermediate actions. On-policy self-distillation (OPSD) offers token-level learning signals through privileged rescoring, but directly applying it to CUA online training presents two challenges: fixed guidance may become misaligned with the student's current state, and guidance-induced probability shifts may conflict with step-level correctness. We introduce ComputerSD, an online self-distillation method for CUAs that converts real-time feedback from executed GUI transitions into guidance for policy learning. A fine-tuned GUI analyzer produces guidance and a step-level value score after each action; the guidance provides privileged context, while the score regulates the resulting OPSD signals. ComputerSD jointly optimizes token-level OPSD and trajectory-level GRPO in a fully asynchronous training framework. On OSWorld-Verified, ComputerSD outperforms outcome-only GRPO by 1.9 and 4.1 percentage points on the general-purpose Qwen3-VL-8B-Thinking and specialized EvoCUA-8B backbones, respectively. Evaluation in out-of-distribution settings further supports the generalizability of ComputerSD. These results demonstrate the effectiveness of learning from real-time feedback through online self-distillation for CUAs.
Abstract (translated)
URL
https://arxiv.org/abs/2609.40253
PDF
-
Enhancing Autoregressive Video Generation via Representation Adversarial Distillation
2026-09-30 16:09:12Fangyu Lin, Xingtong Ge, Lunjie Zhu, Yi Zhang, Zhening Liu, Tianhang Wang, Mengfei Li, Yumeng Zhang, Guanglu Song, Yu Liu, Jun ZhangAbstract
Few-step autoregressive video generation enables efficient streaming synthesis, but errors introduced in early temporal blocks are reused as context and can propagate through subsequent rollouts, leading to detail degradation, structural drift, and unstable motion. Existing distribution matching distillation (DMD) primarily aligns student and teacher distributions in diffusion latent space, but provides no direct supervision over the perceptual quality of decoded videos. We introduce Radian, a representation-space adversarial distillation framework that complements on-policy DMD with real-data adversarial supervision in the feature space defined by a frozen visual foundation model (VFM). During training, Radian sparsely decodes frames from autoregressive student rollouts, extracts multi-level visual representations, and applies lightweight discriminator heads to distinguish generated outputs from real video frames. The DMD objective anchors the student to the pretrained teacher, while the representation-space adversarial objective supplies complementary perceptual and semantic gradients that promote high-quality modes. These additional components are discarded after training, leaving the generator architecture and inference-time denoising budget unchanged. Experiments on Wan2.1-1.3B cover four-step chunk-wise, one-step frame-wise, and minute-long autoregressive generation. Our method achieves a VBench Total of 0.8444 and a VideoAlign Total of 0.8033 under four-step generation, and improves VBench-Long from 0.7805 to 0.8041 over Rolling Forcing while using fewer denoising steps. Controlled comparisons across image, video, and diffusion representations further indicate that the choice of representation spaces induces distinct adversarial signals, and external VFM gradients complement DMD more effectively than adversarial supervision derived from diffusion-internal features.
Abstract (translated)
URL
https://arxiv.org/abs/2609.40037
PDF
-
Multi-Link Safety Filtering for VLA Policies Around Moving Hazards
2026-09-30 15:49:49Yatharth Agarwal, Vijay RaghunathanAbstract
A vision-language-action (VLA) policy can finish a manipulation task while knocking over objects unrelated to it, so task success alone does not show that the policy is safe to deploy in clutter. We study how to keep a pretrained VLA policy clear of such hazards at run time without retraining it, which requires guarding more of the arm than the end effector, following the hazard as it moves, and sharing onboard compute with the policy. Our training-free shield covers the gripper, wrist, and forearm with five ellipsoids and filters every commanded motion through one barrier program against a keep-out ellipsoid fitted from RGB-D perception at reset. Sparse optical flow then carries that ellipsoid's center along with the hazard, with no repeated detection or refitting. Over six simulated hazard-motion conditions, the shield lowers collision from $65.62\%$ to $27.27\%$ and raises safe-success, task completion without collision, from $29.35\%$ to $50.43\%$. Ablations show that guarding the arm links protects beyond end-effector shielding, and that tracking recovers most of the protection lost when the hazard estimate is frozen at reset. On heterogeneous edge hardware, the five-ellipsoid barrier runs on the CPU in $2.2$~ms at the 99th percentile, and trimming the vision--language prefix and taking fewer flow-matching steps shortens each $\pi_{0.5}$ policy call on the integrated GPU from $343$ to $177.3$~ms. On a physical SO-101 arm across four tasks, the arm touched the hazard in 3 of 16 shielded episodes versus 11 of 16 unshielded ones. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.40007
PDF
-
Uni-VLaT: Whole-Body Tactile Adaptation of VLA Policies for Humanoid Loco-Manipulation
2026-09-30 15:04:20Zihao Wang, Shutong Liu, Siqi Zheng, Liu Cao, Ruoqu Chen, Rundong Liu, Yanchao Yang, Mengdi XuAbstract
Physical contact often determines how a humanoid should respond during loco-manipulation, yet vision and proprioception alone are often insufficient to characterize physical interaction, especially when the contact region is occluded. Unlike sparse force or torque measurements at predefined regions, distributed tactile sensing preserves spatially resolved contact patterns across the robot body. We therefore study how to integrate such whole-body tactile information into vision-language-action (VLA) policies for contact-rich control. Our approach, Uni-VLaT, introduces a tactile pathway whose latent state is trained not only for action generation, but also to predict future tactile, proprioceptive, and visual representations. This predictive objective builds a tactile-anchored multimodal context, encouraging a more structured understanding of the physical world. We evaluate Uni-VLaT on five real-robot tasks covering tactile-triggered locomotion, sustained physical interaction, human-robot contact, and loco-manipulation. Uni-VLaT achieves a 75% average success rate, outperforming a baseline without tactile input by 43 points and a tactile-input baseline without predictive supervision by 7 points. Across two pretrained VLA backbones, our method improves Table Sweeping by 30 points on both backbones and Back-Tap Walking by 85-90 points. Ablations further show that contextualized tactile prediction and absolute future targets are critical to performance. These results indicate that predictive tactile learning provides an effective route for extending pretrained VLA policies to whole-body physical interaction.
Abstract (translated)
URL
https://arxiv.org/abs/2609.35450
PDF
-
In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion
2026-09-30 13:58:26Yikai Wang, Xiao Han, Mengmeng Xu, Juan Camilo Perez, Yiannis Douratsos, Sen He, Zijian Zhou, Fei Zhang, Zhaochong An, Juan-Manuel Perez-Rua, Chen Change Loy, Tao XiangAbstract
Few-step autoregressive video diffusion generates a long video by splitting the video into temporal chunks and generating chunk-by-chunk, each through a short sequence of denoising stages. To memorize chunks that are already generated, previous methods reconstruct a clean or less-noisy key--value (KV) cache by additional forwards to build the cache without advancing an output latent. However, every denoising forward itself already computes the in-flight KV of the current chunk. We introduce FlashForward, which directly reuses this cache to avoid the heavy cache-update-only model forwards. After the current chunk completes one denoising stage, its stage-specific cache is already available for the next chunk. Assigning one GPU to each stage therefore lets different chunks occupy different stages concurrently. This early availability has a quality cost: the resulting stage-matched history is noisy, causing appearance and motion drift among chunks. To complement it, FlashForward produces sparse auxiliary clean anchor latents before the corresponding region is generated so the generation trajectories can be stabilized by this two-sided conditioning. The two memories operate at different temporal scales: sparse clean anchor KV supplies coarse, long-range two-sided structural guidance, while dense stage-matched history preserves fine, recent evolution. With up to four GPUs, FlashForward runs $1.16$--$1.69\times$ faster than HiAR and $1.42$--$2.92\times$ faster than Self-Forcing for 16 FPS videos of 20 seconds or longer across 1.3B and 14B backbone scales at 480p and 720p. On VBench, for the 1.3B model at 480p, it achieves higher scores and remains stable at longer durations, demonstrating that FlashForward generates high-quality and temporally consistent videos across durations of 20s, 35s and 65s at a much faster generation speed.
Abstract (translated)
URL
https://arxiv.org/abs/2609.32540
PDF
-
The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends
2026-09-30 13:03:01Zhentao Tan, Jingyi Shen, Yanbo Li, Yao Liu, Yue Wu, Jieping YeAbstract
Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value cache growing with context length. Research thus spans explicit-memory compression, sparse access, recurrent state construction, structured state dynamics, and heterogeneous mechanism composition. This survey analyzes these developments as model-internal contextual memory. We introduce a five-dimensional lens---Memory Representation, Memory Update, Access, Readout, and Integration---describing what is represented, how it changes, what is query-eligible, how it is read, and how readouts form outputs. This lens compares overlapping research lines without imposing one computational model. We reconstruct mechanism-level developments and architectural adoption using 59 release-level records from 14 major model lineages and 11 high-performing open-weight endpoints. First, explicit-memory and recurrent-state methods retain distinct interfaces but increasingly control overlapping memory functions. Second, heterogeneous architectures increasingly coordinate across network depth: layer-wise composition distributes complementary memory processing across representational stages, while cross-layer reuse carries selected memory and routing artifacts forward. Depth thus becomes a dimension along which contextual memory is constructed and managed. Third, these developments motivate a stateful multidimensional memory-routing hypothesis: persistent memory is organized across temporal scope, network depth, substrate type, and representation granularity, while coordinated Sparse Write and Sparse Read determine what is maintained and what contributes to each query. Overall, efficient sequence architecture design increasingly concerns the organization, lifecycle, and selective use of contextual memory rather than an isolated Attention operator.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39661
PDF
-
D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders
2026-09-30 12:35:52Xinyue Xu, Jiahao Zhang, Lijie Hu, Peter Hase, Hao WangAbstract
Sparse autoencoders (SAEs) reveal visual structure in diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be used to control generation. We introduce D-Scope (Diffusion Scope), a framework that connects feature interpretation to generation control through shared visual evidence. D-Scope aggregates SigLIP~2 embeddings of highly activating image patches into visual centroids. Matching target text descriptions against these visual centroids in the shared image-text embedding space then enables retrieval of individual features without per-feature text annotations. The underlying patches provide evidence for inspecting each selection, while spatially masked interventions test the corresponding decoder direction at varying strengths under fixed generation conditions. We characterize 150 SAEs across two model families and five layers, and introduce a benchmark of 100 target concepts with ten contexts each spanning under-specified and explicit-conflict conditions. Our empirical results show that high reconstruction fidelity can coexist with low dictionary utilization and limited visual-evidence coverage. Under per-case best-of-sweep strength selection, contrastive retrieval yields larger mean regional SigLIP~2 gains than direct retrieval across the tested steering configurations, without consistently improving outside-region preservation. D-Scope provides an inspectable framework for evaluating sparse DiT features through their visual evidence and the effects of their decoder directions on generation. The demo is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39625
PDF
-
Sparse Planner: A Hybrid Planner for Efficient Sampling via a Conditional Variational Autoencoder
2026-09-30 12:06:09Wenguang Xu, Giovanni Lucente, Karem Mohamed, Richard MembarthAbstract
Trajectory planning is a core component of autonomous driving systems, where real-time performance and solution quality directly affect safety and reliability. Sample-Based Motion Planning (SBMP) is widely adopted for its ability to approximate near-optimal solutions through parameter space sampling. However, achieving high-quality trajectories typically requires dense sampling, leading to substantial computational overhead and significant runtime variability in complex traffic scenarios. To address this limitation, we propose a Sparse Planner (SP) that improves sampling efficiency by learning the conditional relationship between scene context and effective trajectory parameters using a Conditional Variational Autoencoder (CVAE). By modeling the structure of high-quality sampling distributions, SP directly generates cost-effective samples in the parameter space, significantly reducing the required sampling density while preserving solution quality. Experimental results show that SP achieves lower trajectory cost than the state-of-the-art FISS+ planner while using only one-eighth of the sampling density. In addition, SP demonstrates improved distance-keeping capability in obstacle-rich scenarios and maintains reduced and more stable runtime characteristics, indicating enhanced computational efficiency and predictable runtime behavior.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39570
PDF
-
Spike-driven Vision-Language-Action Model
2026-09-30 11:16:01Shuai Wang, Malu Zhang, Mingquan Liu, Weihui Dai, Dehao Zhang, Jieyuan Zhang, Yimeng Shan, Zijian Zhou, Yang YangAbstract
Vision-language-action (VLA) models bridge multimodal understanding and robotic control, advancing the dominant paradigm for embodied intelligence. However, most existing models rely on large Transformers, whose latency and energy costs hinder deployment on resource-constrained platforms. Through sparse event-driven computation, spiking neural networks offer a promising paradigm for high-performance and energy-efficient computing. Here, we propose the first Spike-driven VLA framework enabling end-to-end direct training for robotic manipulation, which mainly comprises three core components. First, we develop spiking visual and instruction encoders for multimodal perception, encoding visual observations and language instructions into sparse, reliable spike representations for subsequent cross-modal fusion. Then, we introduce Multi-Winner Spike Fusion for instruction-guided scene understanding, using bidirectional top-$k$ winner-take-all spike routing to suppress background interference and yield fused memory. Finally, we propose a Spike Action Chunking Transformer that incorporates spiking cross-attention over the fused memory and the current robot state, enabling efficient end-to-end generation of continuous action chunks for robotic control. Extensive experiments on LIBERO and Meta-World demonstrate that Spike-driven VLA achieves competitive performance with fewer parameters and lower estimated inference energy than conventional VLA models. This work establishes a foundational framework for neuromorphic VLA modeling, paving the way for future advances in resource-efficient embodied intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39514
PDF
-
From Imitation to Reward Discovery: On-Policy Warmup for Agentic RL
2026-09-30 10:13:01Yitong Qiao, Tiantian He, Lei Liu, Yue Shen, Jian Wang, Jinjie Gu, Zhixuan ChuAbstract
Reinforcement learning with a verifiable reward (RLVR) offers a scalable approach to training language-model agents, yet sparse outcome rewards can leave early training with little signal for policy improvement. We identify an On-Policy Acceleration Phenomenon: in our main comparisons, RLVR initialized with on-policy distillation reaches high performance earlier in training and achieves both higher average performance during subsequent RLVR and higher final performance than the alternative baselines. Motivated by this observation, we study On-Policy Warmup (OPW), a teacher-guided stage in which the student trains with teacher supervision on its own interaction trajectories before transitioning to RLVR. Unlike imitation on fixed teacher-generated trajectories, OPW targets states induced by the student's own decisions, including imperfect actions and recovery situations. We provide a theoretical explanation by connecting on-policy reverse-KL distillation to trajectory-level distribution matching. Under a competent teacher and sufficiently small population distillation loss, this connection yields a lower bound on initial verifier success and a corresponding bound on reward-discovery complexity. For group-relative RLVR, we further characterize when increased success probability produces more reward-informative groups. Together, our findings support on-policy distillation as an effective warmup for agentic RLVR and identify initial reward discovery as a mechanism that can contribute to the observed acceleration.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39436
PDF
-
MotionWeave: Learning Motion-Centered Future Dynamics for Vision-Language-Action Policies
2026-09-30 09:00:28Jingqiu Wang, Yan WangAbstract
Vision-Language-Action (VLA) models have recently incorporated world models to provide richer dynamic supervision beyond sparse action labels. However, explicitly predicting future images or videos may include control-irrelevant appearance, while guidance derived from holistic future visual representations and shared global action features may fail to establish timestep-specific correspondence between actions and local visual changes. To address this issue, we propose MotionWeave, a motion-centric future-dynamics framework for action-chunk prediction with two modules: the Action-Induced Motion Grounder (AIMG) and the Horizon Residual Composer (HRC). Specifically, AIMG conditions on action and proprioceptive representations to construct horizon-specific queries that localize interaction regions associated with each future action timestep from current visual tokens. HRC extracts differences between interaction representations at adjacent horizons, encodes them as temporal motion cues, and injects them into action tokens through a gated residual. During training, robot-arm masks rendered from future frames are used to construct KL-based motion-grounding supervision, while inference uses only the current observation. On six MetaWorld tasks, MotionWeave achieves a 75.3% average success rate, an absolute gain of 8.6% over {\pi}0 (66.7%), especially on sustained-interaction tasks. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39324
PDF
-
AHMAD: Adaptive Hybrid Multi-task Vision Learning with Assisted Distillation for Keypoint Detection
2026-09-30 08:56:26Mohammad Mahdi, Nedyalko Prisadnikov, Yuqian Fu, Carmelo Scribano, Danda Pani Paudel, Luc Van GoolAbstract
Generalist multitasking vision models aim to unify multiple vision tasks within a single framework, enabling more efficient and versatile learning. However, handling diverse vision tasks -- spanning dense and sparse predictions -- remains challenging due to their inherently varying output structures. In this paper, we propose AHMAD, a simple yet effective framework for generalist multitask learning that integrates different key vision tasks: semantic segmentation, instance segmentation, depth estimation, keypoint detection, and object detection. Our approach incorporates these five tasks into a unified structure: a shared encoder-decoder with several lightweight task-specific projectors. Under the multitask learning paradigm, we observed a complementary performance gain, achieving a state-of-the-art PQ of 53.1 and an mIoU of 66.5 for COCO-val panoptic and semantic segmentation, respectively. Additionally, for top-down keypoint detection, which typically incurs high computational overhead due to multiple forward passes, we introduce a knowledge distillation-based method that enables a single forward pass over the entire image, greatly improving efficiency. Ultimately, our model delivers a lightweight yet effective generalist multitask learning framework, demonstrating strong performance across five vision tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2609.35490
PDF
-
Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
2026-09-30 07:15:10Kaixing Zhang, Changming Li, Yingdong Shi, Zheng Zhang, Kaitao Song, Wenjie Shi, Jingang Wang, Kan RenAbstract
Textual skills enable large language model (LLM) based agents to accumulate reusable procedural knowledge without updating model parameters. Yet existing skill evolution remains largely confined to the text space: an optimizer must diagnose success and failure patterns, and revise skills solely from long execution trajectories and sparse task outcomes. This text-only paradigm leaves the agent's internal representations, which contain rich records of its evolving execution state, outside the skill optimization loop. We ask whether an agent can improve its external textual skills by reflecting on its own internal representations. We introduce Rep2Skill, a representation-guided framework for self-evolution on agent skills. Specifically, upon the collected agent rollouts, Rep2Skill models their internal model representation trajectories to localize turns that deviate from successful execution dynamics, and it further interprets these signals alongside the execution contexts as actionable textual feedback for targeted skill revision. Experiments on two agent environments with two open-source LLMs show that Rep2Skill consistently outperforms text-only approaches in the self-evolution setting, where the same LLM serves as both executor and optimizer without a stronger external model. This establishes a promising direction moving agent self-improvement beyond text-only reflection.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39149
PDF
-
UGOD: Uncertainty-Guided Opacity and Dropout for Sparse-View 3D Gaussian Splatting
2026-09-30 06:27:05Zhihao Guo, Peng Wang, Zidong Chen, Xiangyu Kong, Yan Lyu, Guanyu Gao, Chenghao Qian, Ziyang Wang, Xinqi Fan, Liangxiu HanAbstract
Sparse-view 3D Gaussian Splatting is prone to overfitting because limited observations leave many Gaussian primitives weakly constrained, yet their contributions are still accumulated through alpha blending. Without uncertainty estimation, the renderer cannot distinguish unreliable primitives from well-constrained ones, allowing their erroneous contributions to corrupt novel-view synthesis. We introduce UGOD, an uncertainty-guided framework that estimates a view-dependent uncertainty score for each Gaussian and uses it to regulate its rendering contribution. A lightweight uncertainty head conditioned on Gaussian attributes and viewing direction predicts this score, which then drives a differentiable opacity-modulation mechanism that attenuates high-uncertainty primitives before compositing. During training, a detached soft-dropout branch applies an uncertainty-controlled continuous keep mask to discourage the model from relying on poorly constrained Gaussians and thereby reduce overfitting. Crucially, detaching the uncertainty score prevents gradients from this stochastic regulariser from biasing or collapsing the uncertainty prediction. Experiments on Mip-NeRF~360 and LLFF show that UGOD improves sparse-view novel-view synthesis while producing more compact Gaussian representations than the compared methods. These results demonstrate that Gaussian uncertainty provides an effective rendering-time control for sparse-view reconstruction.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39089
PDF
-
EarLog: Opportunistic Ear Physiology Sensing toward Personalized Hearing Risk Awareness
Abstract
Many headphone users risk irreversible hearing damage during high-load listening, yet current protection still relies on sound-pressure limits. Clinical tests detect damage after it becomes measurable, leaving the risk-accumulating process unobserved. The acoustic reflex (AR), an involuntary response to high acoustic load, marks when the ear enters a protective state. AR traces are weak, and existing measurements require dedicated probes and controlled conditions that are difficult to maintain during everyday audio. We present EarLog, which turns playback, the dominant interference, into an opportunistic probe. EarLog introduces content-conditioned residual sensing to suppress variations caused by nonstationary content, individual ear acoustics, and device response. It identifies weak AR through loudness-dependent changes and localized spectral irregularities in the residual. A resonance-constrained sparse finite impulse response (FIR) model captures the short-window response. Dual-microphone observations, mild-distortion recovery, and cross-session reference updates keep detection usable under low signal-to-noise ratio (SNR), fit changes, and environmental drift. EarLog runs in real time on an embedded controller using a low-cost dual-microphone add-on. We evaluate it with 81 participants, 16 headphone models, and more than 400 hours of recordings. EarLog achieves 99.0% sensitivity and 98.7% specificity on a clinically referenced benchmark. EarLog records listener-specific AR events during everyday listening, providing data for future longitudinal studies of hearing risk.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12501
PDF
-
Frame Differential On-Policy Self-Distillation for Video Reasoning
2026-09-30 05:25:59Haiying He, Xin Zheng, Shaoli Hu, Shijun Xiao, Xuanhe Liu, Bing Li, Harry YangAbstract
Reinforcement learning (RL) has substantially improved the reasoning ability of multimodal language models through verifiable rewards and increasingly fine-grainedvisual or temporal credit assignment. In video reasoning, however, current RL methods typically train with a fixed sparse frame budget: increasing the number of frames makes autoregressive rollouts expensive, while too few frames may miss temporally localized events and fine-grained visual details. We present \textbf{Frame Differential On-Policy Self-Distillation (FD-OPSD)}, which transfers the useful evidence of dense frame observations to a sparse frame policy during RL training. FD-OPSD compares the policy's token level preferences for the same sampled response under sparse and dense views, and distills the resulting frame differential signal without an external teacher or dense autoregressive rollout. The method preserves sparse-frame rollouts and leaves inference unchanged. Across Qwen2.5-VL-7B and Qwen3-VL-4B on six video reasoning benchmarks, FD-OPSD yields higher overall average performance than the strongest corresponding GRPO, T-GRPO, or Video-KTR baselines across the 16, 32, and 64 frame evaluation settings. These results show that dense visual evidence can be transferred selectively during training through token level self-distillation while retaining sparse frame rollouts and unchanged inference.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39021
PDF
-
C-STRIDE: An Observation-Driven AI Digital Twin for Predicting Basin-Wide Flood Fields from Sparse Stream-Gauge Histories
2026-09-30 05:16:47Yanjie Tong, Phillip Si, Yuan Qiu, Peng ChenAbstract
Emergency managers need to know where floodwater is, how deep it is, and how it will change over the coming hours across an entire river basin. During a flood, however, real-time measurements come from only a handful of stream gauges, and high-resolution hydrodynamic models are too costly to rerun each time new data arrive or to run as large ensembles. We present C-STRIDE, an observation-driven AI digital twin that turns short records from a few stream gauges, together with terrain and rainfall, into basin-wide maps of water depth and extends these predictions up to a day ahead. It is trained on simulations from a calibrated two-dimensional hydrodynamic model and needs no separate data-assimilation step. In the Des Plaines River basin near Chicago, six gauges inform predictions over 4.2 million 30-m grid cells. Terrain improves the predictions most, rainfall keeps errors from growing over longer horizons, and together they reduce errors by about 40% compared with gauge records alone. When future rainfall is known, errors remain near 15% one day ahead, compared with nearly 40% without rainfall. Given real instead of simulated gauge records, the model shifts its predictions toward the observed hydrographs at three of six gauges without retraining, and it runs about 150 times faster than the hydrodynamic model. These results show how sparse gauges, terrain, and rainfall can be combined into fast, continuously updated flood predictions, a step toward operational flood digital twins that still requires testing with real-time data and rainfall forecasts.
Abstract (translated)
URL
https://arxiv.org/abs/2609.39005
PDF
