Matching
-
Perceives but Doesn't Brake: A Perception-Action Binding Gap in Reasoning Driving VLAs
2026-10-20 13:21:14Matteo Cercola, Katie Z Luo, Simone Formentin, Marco PavoneAbstract
Reasoning-augmented vision-language-action (VLA) driving models can perceive and reason about safety-critical hazards yet fail to translate that evidence into safe actions. We characterize this failure as a perception-action binding gap: hazard information is available inside the model but exerts insufficient control over trajectory generation. Using matched simulated counterfactuals and logged driving replay, we show that in-path hazards are actually encoded in the visual representation, but longitudinal plans are dominated by ego-speed history and respond only weakly to hazard proximity or the model's own reasoning trace. Further analysis shows that the trajectory generator is capable of braking but sometimes fails to do so due to the perception-action binding gap. Without retraining or modifying any weights, we inject a hazard-conditioned energy into the frozen flow-matching sampler of Alpamayo-1.5, restoring the missing coupling at generation time. With exact obstacle geometry, guidance cuts footprint intrusion from 58.1% to 14.5% and recovers safe braking whenever sufficient stopping distance remains, eliminating collisions entirely in our braking-relevant closed-loop battery. It also reverses the diagnosed dependence of the plan, from tracking ego speed to responding to obstacle range. These results separate hazard perception from hazard control in driving VLAs, show that unsafe behavior can arise even when the model has both the evidence and the ability to act on it, and propose a simple fix for bridging this binding gap.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28184
PDF
-
De-Diffusing WAMs: Action-Sufficient Direct Prediction for Robot Control
2026-10-20 12:30:58Shaoyi Zheng, Zhongtao Jiang, Yue Peng, Wenbo Lu, Shunchi Zhang, Xi Wang, Shengji WanAbstract
Cascade world-action models (WAMs) use predicted visual futures to condition robot actions, but inherit costly iterative inference from diffusion-pretrained experts. We ask what a single-step predicted future must preserve to support accurate single-step action prediction. In the evaluated WAM, resampling video noise has little effect on downstream actions, yet naively truncating both streams to one step substantially reduces task success. Video-space supervision only partially closes this gap, and a local sensitivity analysis shows that vision prediction errors have highly unequal consequences for action accuracy. These findings motivate DirectWAM, which converts pretrained video and action experts into single-step predictors without stochastic sampling through action-sufficient distillation, while retaining the explicit future-to-action cascade. After learning a one-step action model, we train the future predictor by decoding actions from its own predicted futures and backpropagating demonstration action error through the expert, with an optional future-latent reconstruction loss. The resulting objective evaluates the student-generated future through its downstream control consequences rather than relying on representation matching alone. DirectWAM achieves 97.1% average success across four LIBERO suites and 85.4% on RoboTwin 2.0, outperforming Flash-WAM at the same one-evaluation-per-stream budget. This advantage has also extended to three real-world tasks that we designed. Compared with the full iterative teacher, it reduces inference latency by $28.0\times$.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28122
PDF
-
On-Policy Transition Distillation
2026-10-20 11:37:31Runyang You, Yongqi Li, Tiezheng Yu, Wenjie LiAbstract
On-policy distillation (OPD) consolidates expert capabilities into a single student by matching teacher and student final-layer distributions on student-generated rollouts. We investigate whether depthwise prediction transitions, the changes in predictions between layers, can provide additional task-relevant supervision. Our diagnostic study finds that stronger teacher--student agreement in intermediate transitions is associated with higher answer correctness within questions, with correct responses exhibiting lower mean transition KL across all measured intermediate layer pairs. These observations motivate On-Policy Transition Distillation (OPTD), which augments final-layer distribution matching by aligning teacher and student layer-to-layer log-probability increments on student-generated rollouts. Evaluations across three backbones and eight benchmarks spanning mathematics, coding, and instruction following show that OPTD achieves the best or tied-best overall performance in both dual- and three-domain distillation. In the three-domain setting, OPTD recovers $\approx 90\%$ of the overall teacher--student capability gap, compared with $\approx 75\%$ for OPD.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28048
PDF
-
LoCA: Local Credit Assignment for Reinforcement Learning of Autoregressive Flow-Matching TTS
2026-10-20 11:23:47Jie Liu, Junyu Zhou, Junhao Zhong, WeiSen Tang, Rukai Cai, Haoyue Zhan, Ruiqi Xing, Ling LongAbstract
Reinforcement learning can improve text-to-speech synthesis through feedback on generated speech. However, sentence-level rewards do not identify local errors, while signed regression updates can lead to excessive fitting or repulsion of sampled outputs. We propose LoCA (Local Credit Assignment) for autoregressive flow-matching text-to-speech. LoCA uses ASR-based text alignment to locate content errors in generated speech and redistribute sentence-level advantages across acoustic frames. To improve training stability, we introduce reference-relative positive and negative thresholds that limit continued fitting and repulsion. Experiments on VoxCPM2 show that LoCA reduces sample-weighted content error on a multilingual CV3 evaluation subset by 20.5% and 14.3% relative to the pretrained backbone and GROW, respectively, while improving speaker similarity. LoCA also improves content accuracy on the Seed-TTS-Eval hard subset. Ablation results support the contributions of local credit and threshold-based regression control.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28035
PDF
-
ForeTac: Predictive Contact Guidance for Generative Robot Policies
2026-10-20 10:22:41Zhiyuan Chen, Shuai Chen, Haoran Zhou, Yizhe Zhao, Kaiyuan Yang, Zhixiang Duan, Shaoqing Xu, Ran Cao, Diyun Xiang, Yangwei YouAbstract
In contact-rich manipulation, actions that appear equally plausible from vision can produce different contact outcomes, while reactive control based on current tactile feedback may respond too late to prevent failure. We present ForeTac, a predictive contact-guidance framework organized as a represent-predict-evaluate-guide loop. ForeTac encodes the current tactile state, predicts future tactile latent trajectories conditioned on candidate action sequences, and evaluates each predicted trajectory with a contact-quality objective learned from successful and failed physical interactions. At inference, gradients of this objective are backpropagated through the tactile predictor to guide action generation before execution while keeping all model parameters frozen. We evaluate ForeTac on four real-robot tasks (planar and curved-surface wiping, card swiping, and fragile-object grasping) with diffusion and flow-matching policies. Compared with vision-only Diffusion Policy, ForeTac improves the average task success rate (SR) from 36.3% to 71.3% and the average contact success rate (CSR) from 20.0% to 66.3% across these tasks, and yields gains in both metrics with a flow-matching policy. Component analyses support the learned tactile representation, action-conditioned foresight, and generation-time gradient guidance, while predicted tactile latent trajectories preserve contact-quality ordering. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.18118
PDF
-
In PRAISE of Attributes: Grounding Retrieval Geometry with Query-Conditioned Subspaces for Person Re-Identification
2026-10-20 09:52:06Rajarshi Bhattacharya, Aryan Shukla, Shakeeb Murtaza, Christian Desrosiers, Jose Dolz, Maguelonne Heritier, Eric GrangerAbstract
Person re-identification (ReID) ranks an image gallery using either an image query or a textual query. In image-to-image (I2I) ReID, viewpoint, illumination, occlusion, and background changes can make distractors appear more similar than the true match. In text-to-image (T2I) ReID, incomplete or ambiguous descriptions may omit key visual evidence. We study this problem for vision-language model (VLM) based ReID, where attributes such as clothing color and carried objects provide useful fine-grained matching cues. However, directly using attribute-prompt similarities as retrieval scores is unreliable because templated prompts can be biased, correlated, and poorly calibrated. We therefore propose \textbf{PR}ompt-guided \textbf{A}ttribute-based \textbf{I}nference-time \textbf{S}imilarity \textbf{E}nhancement (\texttt{PRAISE}), a query-side test-time adaptation framework for VLM-based ReID. Instead of treating prompts as scores, \texttt{PRAISE} uses a transferable attribute-prompt bank to construct an \emph{Attribute-Conditioned Subspace} (ACS): a query-dependent low-rank subspace induced by the most compatible attribute prompts. ACS provides a controlled attribute-conditioned geometry for reshaping query--gallery affinities and guiding lightweight inference-time updates without identity or attribute labels. Experiments across multiple I2I- and T2I-ReID benchmarks show that \texttt{PRAISE} consistently improves VLM retrieval backbones and outperforms both generic and ReID-specific TTA baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27944
PDF
-
APRIL: Ambiguity-Aware Expert Routing for Respiratory Sound Domain-Incremental Learning
2026-10-20 09:49:56Xinhong Li, Weiping TuAbstract
Automated respiratory sound classification enables continuous, non-invasive respiratory assessment, yet long-term deployment remains challenging due to domain shifts from evolving recording devices and acquisition periods. When privacy and governance regulations prohibit replaying historical data, sequential learning easily overwrites previously acquired knowledge. Preserving dedicated domain experts prevents parameter interference, but selecting the correct expert at inference is difficult under overlapping acoustic distributions and absent domain labels. To resolve this dilemma, we propose APRIL, an exemplar-free domain-incremental framework for RSC. Built on a shared frozen BEATs backbone, APRIL sequentially inherits and isolates low-rank experts to enable new-domain adaptation without altering earlier models. A multi-level prototype router retrieves the top-two candidate experts and dynamically selects the final model by integrating domain-routing posteriors with classification confidence, adaptively weighted by matching ambiguity. We establish standardized device- and temporal-incremental benchmarks on the ICBHI and SPRSound datasets across forward and reversed domain orders. Evaluated over five random seeds, APRIL consistently achieves the highest final-session average Score among compared continual learning approaches, reaching 64.4% and 65.4% on ICBHI, and 83.1% and 82.2% on SPRSound under forward and reversed sequences, respectively. Crucially, average forgetting remains under 1.0% across all protocols, demonstrating robust domain adaptation and long-term knowledge retention without data replay. Overall, APRIL offers a reliable and privacy-preserving paradigm for deploying continuous respiratory sound classification across real-world healthcare settings.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27942
PDF
-
SGLDet: Spectral-aware Global-Local Dynamic Modeling for Multispectral Aerial Object Detection
2026-10-20 09:06:09Peng Zhang, Shuaihao Han, Tingfa Xu, Jianan LiAbstract
Multispectral aerial object detection aims to exploit spectral-spatial cues to address object detection challenges in complex aerial scenes. Existing methods mainly focus on spectral-spatial decoupling and object-aware spectral-spatial fusion to improve spectral utilization. However, two critical issues remain underexplored: 1) severe foreground-background imbalance caused by large scene coverage hinders reliable object recognition; 2) aerial objects exhibit substantial local variations in scale, orientation, and structure, which hinder accurate localization. To address these issues, we propose SGLDet, a spectral-aware global-local dynamic modeling framework for multispectral aerial object detection, which is motivated by the observation that object semantics are jointly determined by global spectral consistency and scene context, while precise localization requires dynamic feature modulation conditioned on the input spectral and spatial properties. To realize these properties, SGLDet consists of three coordinated components: a Spectral-driven Global Dynamic Modeling module that aggregates spectrally related features across the scene via similarity-guided sparse matching; a Multi-scale Global Context Integration module that constructs a compact scene memory for scene-guided contextual reasoning; and a Spectral-aware Input-dependent Calibration Aggregation module that performs expert-kernel aggregation with scene-guided spectral-spatial calibration to enable adaptive local feature modulation. Extensive experiments on MODA, HOD3K, and DroneVehicle demonstrate that SGLDet achieves superior performance with competitive computational cost. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27883
PDF
-
Manifold Prior Guided Deep Unfolding for Hyperspectral Image Reconstruction
2026-10-20 08:55:16Shuqi Liu, Yingkai Zhang, Lin Gu, Tao Zhang, Ying FuAbstract
Hyperspectral Image (HSI) reconstruction has made substantial progress with the deep unfolding framework by decomposing the problem into a projection module and a denoiser module. Nevertheless, existing methods still exhibit limitations of insufficient matching with HSI data. The issues lie in two aspects: 1) the data-consistency projection module applies a fixed gradient descent step while ignoring the spectral content adaptivity of HSI; 2) the denoiser module either suffers from high computational complexity or is limited to the local receptive field, failing to efficiently capture the global spatial-spectral dependencies. In this paper, we propose a deep unfolding framework centered on a two-stage manifold learning strategy to obtain a degradation-free structural prior, which is then strategically injected into both the projection and denoiser modules. In the data-consistency projection, a prior-guided spectral weight mechanism is introduced to adaptively modulate the weight of spectral band. In the denoiser module, a manifold-guided Mamba is proposed to achieve the structure-aware extraction of spatial-spectral features through prior modulation. Quantitative and visual comparisons on synthetic and real-world datasets show that the proposed method significantly outperforms existing state-of-the-art approaches, while maintaining the structural interpretability of the unfolding framework. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27874
PDF
-
Physical Operating-Condition-Guided Vision-Language Matching for Cavitation Diagnosis in Industrial Pipeline Systems
2026-10-20 08:42:13Yu Sha, Junqi Tao, Deyu Wang, Horst Stoecker, Domagoj Vnucec, Andreas Widlf, Kai ZhouAbstract
Cavitation diagnosis in industrial pipeline systems is challenging because acoustic responses vary substantially with operating conditions, while similar time-frequency patterns may correspond to different cavitation states. To address this issue, we propose a physical operating-condition-guided vision-language matching (POC-VLM) for cavitation diagnosis. POC-VLM first constructs physical operating-condition-aware semantic descriptions by explicitly incorporating sample-specific operating variables into candidate cavitation texts. A time-frequency-conditioned text adaptation module then dynamically aligns these physical semantics with the observed acoustic response, followed by global-local vision-language matching to capture both holistic and localized discriminative patterns. In parallel, a K-nearest neighbours-based non-parametric physical operating-condition prior estimates the physical plausibility of each candidate state and is fused with the vision-language semantic evidence at the decision level. Experiments on three real-world cavitation datasets show that POC-VLM consistently outperforms representative data-driven, multimodal and domain-specific diagnostic methods. Further analyses verify the complementary roles of vision-language semantic matching and physical operating-condition priors, while demonstrating robust performance under varying sampling rates, noise levels and observation durations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27860
PDF
-
ProVe: Proposer-Verifier Decoding
2026-10-20 08:06:37Ziqi Jin, Weiwen Xu, Jiaxi Li, Yujie Zhong, Qi She, Aixin SunAbstract
Speculative decoding accelerates autoregressive (AR) language models by letting a small model draft tokens serially and a large model verify them in parallel. We reverse these roles. Starting from a standard AR checkpoint, we fine-tune the large model into a proposer that predicts a block of future tokens in a single forward pass, then use one additional forward pass to verify the proposed block. This gives ProVe, Proposer-Verifier decoding. The verifier can be a smaller AR model or the proposer itself; the latter gives ProVe-lossless, which reproduces the proposer's greedy AR decoding. Block proposals already provide substantial room for acceleration: with a block size of 16, the proposed block has an average AR-matching prefix of 6.6 tokens on GSM8K. Across six benchmarks with a 32B proposer, ProVe-lossless reaches 2.5x average AR throughput without training a separate draft head. With a small 3B verifier, ProVe reaches 2.7x average throughput at 2.6 accuracy points below AR on the six-task average, providing a controllable tradeoff between speed and accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27815
PDF
-
LatBridge: Efficient and Stable Model Replacement in Latent-Communication Multi-Agent Systems
2026-10-20 08:06:13Jiajun Zhu, Haobo Li, Zixin Chen, Huamin Qu, Wenshuo ZhangAbstract
Multi-agent systems rely on communication to complete tasks, and latent communication passes continuous representations to reduce text generation and re-encoding. However, multi-agent systems must reconfigure agent models, whereas existing latent-communication methods are built for fixed model combinations, so their interfaces may fail after replacement. Our pilot study confirms this interface failure and identifies the requirement for interface reuse after model replacement. We present LatBridge, which connects agent models through a shared Bridge and separate interfaces under a shared latent-communication protocol. After agent model replacement, LatBridge reuses unchanged interfaces, selects matching low-rank interfaces, and combines them through the Bridge, training only missing ones with all models frozen. The Bridge processes source representations in the basic mode and constructs target input without autoregressive generation in the accelerated mode. Experiments support effective communication after model replacement, with mean basic-mode accuracies of 14.8% on MATH and 27.3% on ALFWorld next-action prediction across eight small-model configurations. Analyses examine the factors supporting task accuracy and communication efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27813
PDF
-
OmniInteract: Towards Unified Whole-Body Interaction Control for Dual Humanoids
2026-10-20 08:03:47Yinghao Li, Tianyu Zhang, Zhuohao Li, Yi-Lin Wei, Fa-Ting Hong, Qing Zhang, Wei-Shi ZhengAbstract
Physical interaction is a key capability for humanoid collaboration, requiring coordinated whole-body motion and precise contact. However, learning diverse dual-humanoid interactions faces two major challenges: (1) human-robot morphological differences disrupt contact interfaces and spatial relationships during retargeting, and (2) jointly learning motor skills and partner coordination makes it difficult to retain control fidelity as interaction diversity grows. In this paper, we propose OmniInteract to address these challenges through surface-aware modeling and scalable residual policy learning. First, we introduce Surface Contact-Aware Retargeting, which leverages dense human-robot surface correspondences to jointly retarget both humanoids, preserving explicit interaction contact interfaces and their near-field geometric context. Second, we propose a Scalable Flow-based Interaction Policy for partner-conditioned residual generation. It factorizes dual-humanoid control into a reusable motor foundation and interaction-specific adaptations: partner-aware experts learn corrections over a frozen whole-body motion prior, while conditional flow matching unifies them in a shared residual action space. This enables scalable skill consolidation while retaining pretrained motor capabilities. Extensive experiments demonstrate that OmniInteract improves retargeting fidelity and dual-humanoid coordination while better retaining interaction performance as skill diversity grows. Real-world deployment further demonstrates successful contact establishment, stable whole-body coordination, and recovery from external perturbations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.26043
PDF
-
Toward Agentic AI for the 6G Physical Layer: From Algorithm Discovery to Verified Baseband Silicon
2026-10-20 07:56:10Eric Mittag, Lukas Brechtel, Maximilian Stark, Hans D. SchottenAbstract
6G will be designed faster than it can be built: AI-driven search already proposes physical-layer algorithms at machine speed, while carrying a single one onto embedded baseband silicon remains specialist work. That silicon imposes hard memory and numeric limits, but also exposes cost structures a GPU lacks, and a design flow that never runs on the target sees neither. We present an agentic workflow in which an LLM coding agent implements algorithms on a commercial baseband SoC, optimizes them down to agent-written vector assembly, and validates them on silicon. The agent is guided by a knowledge base of measured platform facts, checked at every step against evaluators it is instructed never to edit, and metered per phase. We showcase the workflow on an AI-discovered orthogonal time frequency space (OTFS) detector portfolio on the open 6G4All platform. It yields twelve kernels that run cycle-exactly on silicon, their optimized versions at 18k-405k cycles (30-660 $\mu$s) per frame. It also yields a new detector shaped by the chip's measured costs that needs 13.9% fewer cycles than the port of the discovered detector while matching its error rate, with a measured edge our evaluation cannot statistically resolve, a structure that a hardware-blind search objective had no reason to find. What is not specific to OTFS is the workflow: an LLM agent exploring an implementation space under real hardware limits, with the cost of every choice measured rather than assumed.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27797
PDF
-
Multi-View Latent Action Pretraining for Cross-Embodiment Robot Learning from Videos
2026-10-20 07:55:43Oliver Hausd\"orfer, Felix Minzenmay, Mani Majd, Maximilian P. Christof, Shiyuan Zhang, Angela P. SchoelligAbstract
Action-free videos are an appealing substitute for costly teleoperated data. Latent action models (LAMs) turn videos into a supervision signal by inferring abstract actions between frames. Existing LAMs observe a single camera view, which resolves 6D robot actions only ambiguously missing out-of-plane movements and potential occlusions. We propose a LAM that ingests synchronized multi-camera views using cross-attention to resolve depth and occlusions before compressing them into latent actions. The latent actions are fed into a policy in which a latent expert and an action expert are coupled by sequential flow matching around a frozen VLM backbone. We further evaluate in strict cross-embodiment settings where task-specific demonstrations come from other embodiments. We show that dual-view LAM pretraining improves the decodability of ground-truth 6D actions by 17% compared to single-view, while scaling single-view data by two orders of magnitude is not sufficient to fully recover out-of-plane motions. The downstream policy improves success rate by +13.5% compared to +6.2% for single-view LAM. A single cross-embodiment is sufficient for skill transfer, and adding a second viewpoint outperforms adding up to four further embodiments. The results transfer to hardware where demonstrations come from a human hand improving success rate by +20% over action-only policies in 850 rollouts. We show that video and robot data are complementary, and that benefits of learning from video are task-dependent. Website: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.27794
PDF
-
VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse
2026-10-20 06:54:08Sicheng He, Yi Pan, Qiuting Yu, Jiaming Huang, Qi Lu, Shuyan Wu, Hongyan Feng, Xuanyu Liu, Jun Zhang, Jie Zhang, Wenqi Zhang, Xuhong Zhang, Jianwei YinAbstract
Flow-matching vision-language-action (VLA) models generate an action chunk by iteratively denoising Gaussian noise, but typically execute only a short prefix before replanning with updated observations. Under this receding-horizon paradigm, the unexecuted remainder---the action tail---is discarded, and the next chunk is regenerated from fresh noise. We show that this discarded tail retains transferable denoising progress: action-tail initialization can match or outperform a native 10-step Gaussian baseline using fewer denoising steps. However, the optimal denoising budget varies substantially across samples, indicating that tail reuse should be adapted to the updated environment. Based on this observation, we introduce VLA-Rolling, a lightweight inference framework that reuses action tails through three stages: action-tail inheritance, per-action confidence estimation, and confidence-guided refinement through renoising and denoising budget allocation, while the underlying VLA remains frozen. Across $\pi_{0.5}$, SmolVLA, X-VLA, and MolmoAct2 on LIBERO, MetaWorld, LIBERO-Plus, and RoboTwin 2.0, VLA-Rolling reduces action-chunk inference cost in all 16 model--benchmark pairs, achieving up to a $1.48\times$ speedup, while improving success rate in 14 pairs by up to $15.08$ percentage points. These results show that action tails are not merely discarded predictions, but reusable intermediate states that enable more efficient and accurate VLA inference. These results demonstrate that the action tail can support the generation of better actions with fewer denoising steps. Our project is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.25043
PDF
-
HumanSkill-4D: Training-Free Language Querying of Animatable Gaussian Avatars in Space and Time
2026-10-20 04:37:26Junsu Kim, Naeun Kim, Dongyoon Han, Seungryul BaekAbstract
We introduce avatar referring segmentation, which selects regions of animatable Gaussian avatars from language queries. A query can also specify a pose or motion to select matching intervals. This lets users interact with avatars for local editing and motion inspection. However, making these selections with existing language Gaussian splatting methods poses two challenges: adjacent parts and garments are hard to separate and may be referred to indirectly (region ambiguity), while fine-grained motions can look alike in RGB (motion ambiguity). We address these challenges with HumanSkill-4D, a training-free framework that shares a multimodal large language model (MLLM) and geometric operators across avatars. For each avatar, a semantic memory links body-part and garment categories to persistent Gaussian regions and appearance descriptions. The MLLM uses category names and descriptions to select categories by appearance, relation, or function. To find matching intervals, it composes operators into programs that check query conditions on driving joint trajectories stored in a motion memory. These category choices and operator outputs make selections traceable, while composing or adding operators supports new motion conditions. To evaluate this task, we introduce three human-annotated benchmarks and show that HumanSkill-4D outperforms the baselines in part segmentation and 3D and 4D referring segmentation, with compact memories and only minutes of setup per avatar.
Abstract (translated)
URL
https://arxiv.org/abs/2610.24452
PDF
-
Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
2026-10-20 03:12:50Abhijeet Sinha, Sundari Elango, Dianbo LiuAbstract
Many reinforcement learning (RL) problems admit multiple terminal solutions of comparable quality, where the goal is not to identify a single optimum but to represent a diverse set of high-quality outcomes. Nevertheless, policies trained by standard expected return maximization routinely collapse onto a small subset of outcomes, a phenomenon commonly attributed to insufficient exploration or weak regularization. We show that this explanation is incomplete: outcome level mode collapse is a structural consequence of the expected-return objective itself. Under idealized learning dynamics, the log-probability ratio between any two outcomes evolves linearly in their reward difference, implying exponential ratio divergence and inevitable collapse independent of the exploration strategy, entropy regularization, or optimization algorithm. We identify the source of this pathology as the probability multiplier inside the expectation and propose a minimal correction: inverse probability scaling, which removes outcome-frequency amplification from the learning signal, fundamentally changes the learning dynamics, and provably yields reward-proportional terminal distributions, preventing collapse in multimodal settings. We instantiate this principle in Group Relative Policy Optimization (GRPO) as a drop-in modification, IPS-GRPO, requiring no auxiliary models or architectural changes. Across different reasoning and molecular generation tasks, IPS-GRPO consistently reduces outcome-level mode collapse while matching or exceeding baseline performance, suggesting that correcting the objective rather than adding exploration heuristics is key to reliable multimodal policy optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2601.21669
PDF
-
HealBench: A Fine-Grained Benchmark for Evaluating Psychological Comfort in Text-to-Image Generation
2026-10-20 02:31:31Junjie Xu, Yuzhe Yang, Rui Yang, Luwei Xiao, Wenxin Wu, Xingjiao Wu, Liang HeAbstract
Despite advances in photorealism, semantic fidelity, and aesthetics, text-to-image generation and image editing remain understudied in a human-centered dimension: whether their outputs feel psychologically comforting. Grounded in cognitive evaluation theory, we define psychological comfort as an affective response shaped by viewers' appraisal of restorative and emotionally supportive visual cues. We introduce HealBench, a fine-grained benchmark of 30,000 high-quality image-text pairs spanning 19 categories and 92 subcategories, selected from 100,000 candidates through a human- and expert-in-the-loop pipeline combining vision-language model matching, human preference models, expert filtering, and exemplar-guided augmentation. We also construct HealBench-Eval, a feature-clustered evaluation set of 1,095 instances. Using HealBench-Eval, we conduct objective and subjective evaluations of 14 representative image generation models and prompt-rewriting strategies. Results reveal a gap between conventional visual quality and perceived comfort: strong semantic alignment and aesthetics do not guarantee emotionally restorative images. Reinforcement learning experiments further show that HealScorer can serve as a reward signal for assessing and improving the emotional and restorative quality of generated images. These findings establish psychological comfort as a distinct dimension of human-centered image generation and position HealBench as a foundation for affect-aware generative models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27516
PDF
-
Structured-Token Attention for Fine-Grained mmWave Liquid Identification
2026-10-20 02:27:39Junseo Min, Joongheon KimAbstract
Fine-grained liquid identification requires a classifier to distinguish similar substances from compact millimeter-wave measurements. We investigate structured-token attention, which represents a radar feature tensor through complementary antenna, feature, branch, and global views. The proposed StructAttn model embeds these views into eleven tokens and combines them with a three-layer transformer. Experiments on the public FG-LiquID data cover 30 liquids and 3,000 samples. Over five seeds on the released split, StructAttn achieves 96.70\% mean best-epoch accuracy, matching the original-recipe MMNet baseline and exceeding a scalar-token attention model by 1.50 percentage points. A five-seed probability ensemble reaches 97\%, corresponding to 18 errors among 600 test samples. Final-epoch and five-fold results complement the checkpoint-selected comparison, with StructAttn obtaining 95.30\% out-of-fold accuracy. Token and feature analyses show that structured views are useful for prediction, while residual confusions concentrate in water, soft-drink, and edible-oil classes. These results support structured tokenization as a practical design choice for attention-based liquid recognition.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27512
PDF
