Attention
-
ProtoPur: Prototype-Purity Pseudo-Labeling for Weakly Supervised Instance Learning in Pathology
2026-10-14 16:16:48Chen Shu, Chengyang Zhang, Boyu Fu, Ting Yin, Wenchuan Zhang, Jie Chen, Yuhao Yi, Hong BuAbstract
Weak bag-level labels are widely available in computational pathology, whereas reliable instance-level annotations for whole-slide images remain expensive and ambiguous. Weakly supervised multiple instance learning (MIL) achieves strong bag-level classification, but instance-level supervision from attention scores, model predictions, negative bags, or spatial refinement may fail to identify class-specific local evidence. We propose ProtoPur, a prototype-purity pseudo-labeling method for weakly supervised instance-level learning in pathology whole-slide images. ProtoPur estimates class-balanced local purity over prototype regions constructed from frozen foundation-model features, and assigns pseudo-labels to high-purity regions strongly associated with a target class. This purity-first design separates class-specific evidence from negative or shared morphology, with coverage used only to ensure sufficient pseudo-label assignment. We provide a PAC-style analysis showing that the risk of an instance classifier trained with ProtoPur pseudo-labels can be decomposed into a standard uniform-convergence term and a ProtoPur-specific pseudo-label noise term, comprising selected-region mismatch and a coverage residual. Experiments on three public whole-slide image datasets with two pathology foundation encoders show that ProtoPur consistently improves instance-level performance across multiple MIL backbones while maintaining competitive bag-level performance. Pseudo-label quality comparisons on two public datasets further demonstrate that prototype-purity selection provides stronger instance supervision. These results suggest that the foundation-model features contain exploitable instance-level supervision signals, and ProtoPur is a way to reveal and use these signals from weak bag labels without requiring dense instance annotations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.15669
PDF
-
Hybrid supervised instance segmentation by learning label noise suppression
2026-10-14 16:10:03Linwei Chen, Ying Fu, Shaodi You, Hongzhe LiuAbstract
To reach top accuracy, current fully supervised instance segmentation methods severely rely on large-scale pixel-wise labeled datasets. They are usually expensive and time-consuming to obtain. Though weakly or semi-supervised methods utilize cheap bounding box labeled, image-level labeled or unlabeled samples to save the labeling cost, their performance is largely sacrificed. To save labeling cost without losing much performance, in this paper, we present a pipeline that can utilize economical bounding box labels and accurate pixel-wise labels in a hybrid way. Specifically, we design two ancillary models to learn label noise suppression and obtain accurate pseudo pixel-wise labels from bounding box labels for training. One is designed to suppress mislabeling between foreground and background, and the other is designed to suppress noise from mislabeling of instances. Moreover, we exploit category-aware spatial attention module, category constraint module, instance constraint module, and self-learning training approach to improve the accuracy of pseudo labels. Experiments on the PASCAL VOC 2012 and the Cityscapes datasets show that our method can achieve competitive performance with much less labeling cost.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20412
PDF
-
FOLD: Position-Free Far Memory with Local Order for Long-Context Speculative Decoding
2026-10-14 15:55:10Shuxuan Li, Jialiang Kang, Yanghao Zhou, Ziye Zhu, Xiao YangAbstract
Speculative decoding accelerates LLM generation through lightweight drafting and parallel verification. It is particularly promising for long inputs, where KV-cache access costs can be amortized over multiple accepted tokens. Yet most drafters are trained on short sequences and degrade on long inputs, while long-context training is costly. Existing training-free approaches restrict the context window, rescale positions, or augment recent context with retrieved distant entries. Drafters, however, read target hidden states that already encode contextual and positional information, and their lightweight architecture makes full-history attention affordable. We propose FOLD, a training-free method that preserves exact local positions and treats all distant entries as far memory at a shared position. To counter attention dilution as the memory grows, we sharpen attention within it to emphasize relevant entries while separately controlling its total weight relative to the local window. Across six target-drafter pairs and diverse benchmarks of up to 256K tokens, FOLD predominantly delivers the highest speedup, with the best case more than doubling the speedup over autoregressive decoding, from 2.08$\times$ to 4.22$\times$.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20392
PDF
-
NeuroDETR: Multiscale Discrete Spatiotemporal Tokenization for Asynchronous EEG Event Detection
2026-10-14 15:27:34Yaozhi Wen, Kun Zhao, Wei Wei, Haoyang Chen, Kangning Wang, Yi Sun, Shaowei Gu, Dingkun Liu, Shuang Qiu, Huiguang HeAbstract
Asynchronous EEG event detection supports practical brain-computer interfaces by identifying event classes and temporal boundaries directly from continuous recordings without predefined event boundaries at inference time. The primary challenge lies in extracting event-related patterns embedded in ongoing background activity. To address this, we propose \textbf{NeuroDETR}, a discrete spatiotemporal multiscale framework that combines structured tokenization with event-aware feature refinement. Multiscale temporal codebooks capture brief responses and sustained dynamics, while Spatial-Pyramid VQ hierarchically encodes spatial structure across EEG channels. These complementary representations form a compact event memory for jointly classifying events and estimating their onsets and offsets. Before tokenization, we apply FOCAL, an event-aware sparse attention module that uses predicted event presence to guide temporal feature refinement and spatial aggregation, emphasizing likely event periods while preserving context across the recording. Experiments on eight EEG datasets that span diverse paradigms demonstrate state-of-the-art performance. These findings provide a basis for the development of BCI systems that recognize meaningful neural activity during continuous interaction and monitoring.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20349
PDF
-
Beyond Static Cues: Unified Dynamic Detection of MLLM Backdoors via Dual-Flow Trajectory Analysis
2026-10-14 15:05:49Yinzhen Huang, Jiahe Xie, Yitong Sun, Ruochen Zhang, Xingxing WeiAbstract
Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, yet their susceptibility to backdoor attacks remains a formidable challenge. While existing defenses have evolved from visual-centric patch cues to unsupervised internal attention statistics, they are fundamentally constrained by a reliance on static snapshots and attack-specific heuristics. Given the intricate interplay between dual modalities, the vast design space for multimodal triggers allows diverse threats, such as textual injections, sub-perceptual noises, and coordinated cross-modal triggers, to easily circumvent such rigid priors, particularly when attack types are unknown in real-world applications. In this paper, we rethink backdoor detection by shifting the diagnostic paradigm from static observations to dynamic output evolution. We observe that a successful attack inevitably hijacks the model's decoding trajectory, skewing internal modal contributions during generation while maintaining an abnormal output invariance despite input perturbations. To capture this behavior, we propose EVO-Detect, a unified detection framework that monitors the dynamic evolution of internal signals during early decoding steps through two complementary channels: Attention Flow and Logits Flow. The attention branch measures how image-text attention allocation evolves during early generation, whereas the logits branch quantifies the sensitivity of the output distribution to modal perturbations through interventional ablations. We then convert these trajectories into compact sample-level metrics and normalize them against negative-control signatures so that natural perturbations are less likely to be mistaken for backdoor evidence. Extensive evaluations show that our approach substantially outperforms state-of-the-art baselines such as BYE and TCAP across diverse attack families.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20319
PDF
-
GLoD-LVSM: Learning Geometry-Grounded Continuous-LoD Scene Representations for Large View Synthesis Models
2026-10-14 14:25:44Weikai Lin, Nicholas Milef, Carl S Marshall, Grant Kaijuin Yang, Todd Keeler, Yuhao ZhuAbstract
Large view synthesis models (LVSMs) reconstruct scenes from sparse views and render novel views quickly, but they incur unnecessary storage and rendering costs due to token redundancy. We present GLoD-LVSM, a compact, geometry-grounded scene representation for LVSMs with continuous levels of detail. First, instead of learning a fixed set of scene anchor initializations, GLoD-LVSM learns a continuous field that initializes a flexible number of anchors to match the desired budget. A condenser then aggregates scene information into these anchors, with both the field and condenser trained end-to-end. Second, the condenser infers reference-token and anchor geometry to guide compression through geometry-grounded attention, improving rendering quality and enabling frustum culling during decoding. Compared with existing LVSM scene-compression baselines, GLoD-LVSM achieves the best trade-off between rendering quality and scene token count. Compared with the uncompressed base model, GLoD-LVSM reduces the scene-token count by 33.4% and accelerates rendering by $1.23\times$ with no quality loss. Under a relaxed quality-loss budget, the reduction increases to 85.5%, with $3.00\times$ rendering speedup. Further analysis reveals that view-synthesis supervision yields emergent scene depth and self-organized anchors that align with surfaces and adapt their density to local texture complexity. Beyond rendering, we further show that our scene representation also supports scene-semantic understanding, highlighting its potential for broader downstream tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20254
PDF
-
PAWA: Panoramic Action-conditioned World Modeling for Multiple Agents
2026-10-14 14:17:23Siqi Yang, Yimu Wang, Ziqi Cai, Chengxuan Zhu, Shuchen Weng, Erwin Wu, Zhaofei Yu, Kaipeng Zhang, Boxin ShiAbstract
A multiplayer world model must predict how the independent actions of several players change a shared environment, including changes outside a player's current field of view. A point-of-view (POV) video captures such changes only after they enter its field of view, whereas panoramic video records the surroundings in every viewing direction and has served as an intermediate representation of the world state in recent world models. Learning this task therefore requires synchronized POV and panoramic videos of interacting players together with their actions, yet no existing dataset provides this combination in Minecraft, an established testbed in which players act independently in a shared, modifiable 3D world. We present PAWA, a dataset and framework for action-conditioned panoramic multiplayer world modeling. The dataset pairs each player's POV video with world-stabilized panoramic video and aligned actions. Its distributed pipeline decouples CPU gameplay capture from GPU rendering, scales beyond 64 simultaneous players, and re-renders each recorded session under new observation configurations without replaying the gameplay. On this dataset, we develop a dual-tower model that jointly predicts POV and panoramic video and couples the two streams through cross-attention that aligns tokens observing the same direction in a shared world frame. We further introduce a quadratic-phase player encoding that provides many more player codes than existing rotary codes at the same embedding dimension. Experiments show that PAWA outperforms state-of-the-art multiplayer world models in POV prediction quality while also producing high-fidelity panoramic predictions. The dataset and collection pipeline are open source to support further research on multiplayer world models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20240
PDF
-
ObjDream: Guiding Vision-Language-Action Models with Object-Level Understanding and Future State Prediction
2026-10-14 14:06:03Huailiang Ma, Yuxuan Li, Ziyi Zhao, Xinkai Wang, Mingyu Li, Xinyu Guo, Lifeng Zhu, Aiguo Song, Cewu Lu, Jianhua SunAbstract
Vision-language-action (VLA) models have emerged as a powerful paradigm for robotic manipulation, enabling robots to generate actions from visual observations and language instructions. However, most existing VLA models still operate on image-level visual representations inherited from pretrained vision-language backbones, while lacking fine-grained object understanding for manipulation. As a result, their robustness can degrade under out-of-distribution object layouts, clutter, and background variations. To address these limitations, we introduce ObjDream, an object-centric VLA framework centered on object-level understanding and future object state prediction. ObjDream uses a spatio-temporal object encoder to organize visual observations into temporal object slots, where persistent object identity and dynamic object state are represented through separate channels. These structured object representations are inserted into the token sequence of the vision-language model (VLM), where identity-guided routing modulates VLM attention to the corresponding object tokens. In addition, an action-conditioned object dynamics module predicts compact future object states relevant to manipulation during training, explicitly supervising object state evolution under robot actions without requiring future prediction at inference. Experiments on LIBERO, LIBERO-Plus, and RoboTwin 2.0 show that ObjDream improves generalization under diverse distribution shifts and scene perturbations. Real-world robot experiments further demonstrate that ObjDream transfers to physical manipulation settings with novel object arrangements and background changes.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20223
PDF
-
Continual pretraining Prostate MRI ViT Encoder for task alignment
2026-10-14 13:57:23Bilal A. Sidiqi, Yipei Wang, Shaheer U. Saeed, Shiqi Huang, Daniel C. Alexander, Yipeng HuAbstract
Building foundation models for MRI has emerged as a promising direction for advancing medical image analysis and improving accessibility of task specific models. Existing approaches primarily focus on effective pretraining strategies and evaluating their performance across diverse downstream tasks. While these methods show performance gains, limited attention has been given to understanding task alignment between pretraining and downstream objectives. Unlike language models, where the two stages are naturally aligned, such alignment is less evident in vision based applications. Motivated by this gap, we explore continual pretraining. Specifically, continually pretraining a pretrained ViT encoder using Low-Rank Adaptation (LoRA) on a prostate segmentation task to enhance task alignment and downstream performance. We further perform layer-wise representational analysis using Centered Kernel Alignment (CKA) to assess representational shifts and their correlation with task outcomes. Our experiments show improved performance in 3 of 6 downstream tasks and comparable results in the others. Our Feature analysis reveals that, for segmentation tasks, continually pretrained encoder features exhibit greater similarity to those of the finetuned encoder than the original pretrained encoder, correlating with observed performance gains.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20217
PDF
-
Retrieval-Augmented Large Language Model Decision-Making for Autonomous Driving Guided by Chinese Philosophical Wisdom
2026-10-14 13:28:56Xiaojun Bi, Xiaoyuan Ma, Yiwen Sun, Tianren Huang, Chaoran Liu, Bokai Huang, Hao Yang, Baichuan MoAbstract
Autonomous driving decision systems must balance safety, efficiency, and social norms in complex traffic interactions. Philosophical and ethical considerations have received limited attention in existing autonomous driving decision-making approaches based on numerical optimization, sequence prediction, and large language models (LLMs). We propose Chinese Philosophical Wisdom-Guided Driving (CPW-Drive), a closed-loop retrieval-augmented generation (RAG) framework that incorporates value guidance derived from Chinese philosophy into autonomous driving decision-making. Using Chinese Confucian thought as its knowledge source, CPW-Drive consolidates LLM-extracted keywords from relevant classical texts into driving-relevant value principles through manual screening and validation. It then contextualizes these principles through scenario-specific cases to form retrievable and reusable value guidance. We further propose Physics-aware Spatial Similarity Retrieval (PSSR), which compares vehicle layouts and velocity-extrapolated states to retrieve physically relevant historical cases. On Highway-env's multilane highway-driving task, CPW-Drive achieves success rates of 93.0%, 86.0%, and 72.0% across three traffic configurations. These results outperform the strongest baseline by 8.0, 22.5, and 25.0 percentage points, respectively. Across all configurations, CPW-Drive achieves the highest collision-free step count and maintains a low lane-change frequency. The results suggest that structured value guidance can improve simulated closed-loop safety and stability while introducing efficiency and latency trade-offs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.03948
PDF
-
TreeSpark: Learning to Draft the Trees You Verify for Speculative Decoding
2026-10-14 13:21:09Jihao Zhao, Qianyu Jiang, Shuaishuai Zu, Pengfei Li, Guanghuan Fang, Ben Feng, Biao Qin, Zhibin Wang, Baochuan YangAbstract
Parallel drafters such as DFlash and DSpark reduce proposal latency, but early mismatches limit how much of each block can be accepted. Retaining alternatives introduces parent states and candidate choices that reference-conditioned training does not directly supervise. We introduce TreeSpark, a unified training and inference framework extending the semi-autoregressive DSpark architecture. It constructs parent-conditioned candidate trees from one backbone pass and replays their expansion, pruning, and budgeted packing during training. Survival negative log-likelihood weights retained edges by reference-derived path mass, while a capped coverage hinge promotes target-important alternatives near local selection boundaries. Both objectives reuse reference-chain target distributions without additional target forward passes. We evaluate greedy decoding with Qwen3-4B and Qwen3-8B on nine general benchmarks and six writing domains. Across targets and suites, TreeSpark improves mean acceptance length over DSpark by 23.4% to 31.6% and mean single-request throughput by 15.1% to 25.0%. Batched Qwen3-4B throughput improves by 12.6% to 17.2%. At fixed attention capacity and inference policy, the proposed supervision further improves mean acceptance length by approximately 6.4% and mean system throughput by 4.2% to 5.0% on Qwen3-4B.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20175
PDF
-
Attention-Based Spatio-Temporal Approach for Fire and Smoke Detection
2026-10-14 13:00:33Alireza Mirrashid, Mohammad Khoshbin, Ali Atghaei, Hassan ShahbaziAbstract
In various industries, smoke and fire are two of the most important threats in the workplace. One of the common methods for detecting smoke and fire is the use of infrared thermal and smoke sensors, which cannot be used in outdoor applications. Therefore, the use of vision-based methods seems necessary. The problem of smoke and fire detection is spatiotemporal and requires spatiotemporal solutions. This paper presents a method that uses spatial features along with temporal-based features to detect smoke and fire in the scene. It consists of three main parts; the task of each part is to reduce the error of the previous part so that the final model has a robust performance. This method also uses transformer modules to increase the accuracy of the model. The results of our model show the proper performance of the proposed approach in solving the problem of smoke and fire detection and can be used to increase workplace safety.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20141
PDF
-
StreamErase: Towards Ultra-Fast Streaming Video Erasing
2026-10-14 12:55:16Zhuobai Dong, Xiaobing Tu, Xiantao Zhang, Jinkui Ren, Yinggui Wang, Yue Ma, Linfeng ZhangAbstract
Current video object removal methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present StreamErase, enabling sub-second latency with up to 26 FPS streaming generation on a single GPU. Our approach first augments a text-to-video model with mask input to generate high-quality videos that erase target objects and synthesize coherent backgrounds, but does not perform inference on the fly. As such, we progressively transfer the erasing capability from a powerful bidirectional foundation model to an efficient unidirectional streaming eraser, enabling long-horizon erasing without sacrificing visual fidelity. Several key challenges arise when generating videos over long, potentially infinite horizons: (1) bridging the domain gap from training on finite length and extrapolating to long horizons, (2) sustaining high quality by preventing error accumulation, and (3) maintaining fast inference, without increasing computational cost as the context grows. To address these challenges, we carefully designed sliding-window causal attention with attention sinks. By incorporating self-rollout with attention sinks and KV cache rolling during training, we simulate inference-time extrapolations with a fixed context window, enabling constant-speed generation of arbitrarily long videos. Finally, we establish a dedicated benchmark, LongErase, for streaming long-video object removal. Our model achieves strong performance compared to existing video object erasing models and generalizes well to real-world video scenarios, uniquely enabling infinite-length streaming. With StreamErase, users can input a mask and see the erasing results unfold in real-time, delivering a truly interactive experience.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20137
PDF
-
ACR-Net: Mitigating Semantic Dominance via Contrastive Acoustic-Semantic Decoupling
2026-10-14 12:42:55Mengke Zhang, Yanda Shao, Tianhe Wu, Kai FengAbstract
Speech Emotion Recognition (SER) models and Audio LLMs fail when vocal tone contradicts textual semantics. Extensive training on congruent data engenders a rigid semantic prior, causing "Semantic Dominance", a severe text bias during cross-modal conflicts. We introduce the ASPIRE benchmark of adversarial audio-text pairs across four conflict types, alongside two metrics: Semantic Overconfidence Penalty (SOP) and Latent Decoupling Degree (LDD). Unlike fusion methods that merely re-weight collapsed features, our Acoustic Conflict Resolution Network (ACR-Net) uses Cross-Modal Attention and Contrastive Decoupling Loss to disentangle contradictory representations into orthogonal latent spaces. Experiments show existing models fail under polarity conflicts due to extreme semantic overconfidence. Conversely, ACR-Net preserves acoustic fidelity, maintaining high LDD to drive SOP near zero, achieving superior Acoustic Accuracy (ACC) in both adversarial and standard scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2610.20114
PDF
-
Choosing the Number of Attention Heads from Intrinsic Dimension: A Small-Scale Study
2026-10-14 10:50:40Arjun Boya, Charan Sai Bandaru, Masthanaiah Pillimetla, Kavana ChidanandappaAbstract
The number of attention heads in a transformer is usually set by convention or grid search. We test a simple heuristic for setting it in advance: estimate the intrinsic dimension of token representations without labels, and use roughly that many heads. We estimate intrinsic dimension with a nested-dropout VAE trained on DistilBERT embeddings of WikiText-2, choosing the KL weight at the knee of the VAE's rate-distortion curve rather than by hand. This gives $k^*=9.2$ (95% CI [8.6, 9.8]). In a small 4-layer transformer trained from scratch, 10 heads and 32 heads are statistically equivalent on SST-2 and on MRPC (paired TOST over 10 seeds, $\pm1$ point margin), with 69% fewer attention parameters for the 10-head model. Training 10 heads from the start also slightly outperforms training 32 heads and pruning to 10 (0.6 points, $p=0.008$). The evidence is narrow: two classification tasks, one small architecture, no pretrained models, and no formal link between intrinsic dimension and head count. We present the result as a practical heuristic worth testing at larger scale, not as a general principle.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19966
PDF
-
Complementary Future Token Pruning for World Action Models
2026-10-14 10:39:16Baekseung Kim, Junhoo Lee, Sohyeon Hong, Suhyun Jeon, Minkyu Kim, Seungyeon Kim, Donghoon Han, Nojun KwakAbstract
World action models (WAMs) jointly predict future visual states and robot actions, but processing dense future-frame tokens incurs substantial inference latency. We propose CF-Prune, a training-free framework for pruning future-frame tokens in pretrained WAMs. Our key insight is that future visual predictions support action generation and therefore need not preserve every visual detail required for high-fidelity video synthesis. CF-Prune combines instruction and action attention to identify task-relevant tokens during the initial denoising forward pass, even when future-frame and action representations remain highly noisy. An entropy-based phase identification mechanism further retains dense computation during precision phases to mitigate pruning-induced performance degradation. Experiments on RoboLab, RoboCasa, and real-world manipulation tasks demonstrate consistent inference speedups. At a 35% pruning ratio, CF-Prune achieves average speedups of 1.19-1.27x while improving task success rates. At a 50% pruning ratio, it achieves 1.29-1.33x average speedups on both simulation benchmarks, with overall success rates within 1.0 percentage point of the baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19957
PDF
-
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
2026-10-14 08:36:31Linhao Zhong, Bozhen Fang, Xuehao Wang, Duochao Shi, Zekai Luo, Guangming Yao, Yi Yuan, Hao Chen, Jingdong Chen, Chunhua ShenAbstract
Self-distillation in agentic reinforcement learning has produced a growing number of methods. However, existing evaluations often reuse published baseline scores under differing experimental conditions, provide few direct comparisons among contemporaneous methods, and give limited attention to training stability and computational cost. These limitations obscure the source of reported gains and the practical strengths and weaknesses of competing methods. Costly agent training further motivates a common basis for comparison. To address these gaps, we compare ten representative methods against GRPO on ALFWorld, ScienceWorld, Search-QA, and WebShop across three model sizes. Our study comprises 132 training runs totaling 12,124.4 recorded H800 GPU-hours, with repeated evaluations over eight rollout seeds for the pretrained backbones and all eleven trained methods. Beyond final task performance, we examine training progress, stability, and measured computational cost. Our evaluation yields three key findings. First, gains over GRPO remain limited in scope, with no method consistently outperforming it across settings. Second, strong final performance can mask unstable training. Third, additional training cost does not consistently translate into better performance. We establish this benchmark to support fair, comprehensive comparison and guide future research toward reliable and cost-effective improvements in agent training. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.19789
PDF
-
Beyond Reachability: A Relation-Semantic Reasoning Framework for Biomedical Multi-hop QA
2026-10-14 08:09:02Ziyang Ling, Ziyi Chen, Ronald X. Xu, Mingzhai SunAbstract
Biomedical multi-hop reasoning over knowledge graphs requires identifying a semantically valid relation sequence that supports the answer. Existing methods can retrieve correct answers, yet often rank them poorly within a large pool of seemingly relevant candidates. Even when a correct answer is retrieved, its associated evidence and reasoning path may fail to support the relation composition required by the question. We term this disconnect between answer reachability and evidential validity the reachable-but-invalid problem. We present ReSemReason, which shares a question-induced distribution over typed, directed relation schemas between candidate discovery and evidence selection. Schema compatibility guides graph search; ReSemAttn then uses relation-conditioned key/value projections and an uncertainty-weighted path prior to attend to candidate-specific evidence. A separate absolute-support score complements normalized attention when all retrieved paths are weak. The reported experiments on BioHopR, PrimeKGQA, and MedReason show improvements in answer ranking and answer-set quality. Path-discrimination analyses examine the distinction between endpoint correctness and evidential support. We also specify matched controls for search, attention, and schema uncertainty.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19754
PDF
-
Mitigating Video Hallucinations via Attention-Guided Representation Perturbation
2026-10-14 07:50:08Zhixin Cai, Ruoqi Yuan, Xinchen Yang, Zhuofan Chen, Jun Bai, Chuantao Yin, Wenge RongAbstract
Video large language models (Video LLMs) often generate responses unsupported by the input video. Contrastive decoding (CD) can mitigate these hallucinations, but its effectiveness depends on how the negative branch weakens visual evidence. Existing methods rely on predefined perturbations or masking guided by question reconstruction, offering limited control over the model's visual reliance during answer generation. We introduce Attention-guided Representation Perturbation for Contrastive Decoding (ARP-CD), a training-free framework for constructing contrastive negatives directly in representation space. ARP-CD uses the attention mass assigned to visual tokens at the answer-prediction position to guide bounded gradient updates of the language model's input visual hidden states. These updates reduce visual attention and produce a negative input, whose predictions are contrasted with those of the original branch throughout generation. Experiments across four Video LLMs and four benchmarks show that ARP-CD outperforms representative training-free baselines in most model--benchmark settings, reducing hallucinations while improving general video understanding. Further analyses show that attention-guided perturbation directions improve negative quality and that the resulting negatives provide effective contrastive references for correcting the original predictions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19728
PDF
-
Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE
2026-10-14 06:04:04Yuhang Hu, Junlin Lyu, Yuan Fang, Xiaoying Shen, Lechen Zhang, Jiong Lin, Judah Goldfeder, Steven Tian, Hod LipsonAbstract
Gaze coordinates attention in human interaction through coupled eye, head, and eyelid motion. A humanoid robot must choose where to look while generating a suitable movement toward that target; fixed tracking rules alone do not model the temporal structure of human gaze. We separate these tasks with an asynchronous vision-language model that selects a scene referent, a reactive perception module that maintains fixation, and a Realistic Gaze Transformer (RGT) that generates target-conditioned motion. RGT is a Transformer-VAE trained on markerless human recordings retargeted to the robot's 11-DoF joint space: self-supervised pretraining encodes recent full-head history, and autoregressive fine-tuning exposes the model to its own predictions during rollout. At inference, a four-dimensional binocular-eye trajectory conditions coordinated neck and eye motion; an auxiliary blink predictor triggers eyelid templates during playback. On a two-second benchmark in which all controllers receive the same ground-truth target, RGT-Base obtains the lowest reported overall seven-joint MSE, and physical demonstrations show the integrated targeting and control pipeline. The evidence establishes robot-space kinematic fidelity and real-time RGT inference; perceived naturalness and open-vocabulary target-selection accuracy remain questions for controlled evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19635
PDF
