Relation
-
VIGOR: Benchmarking Visual Rationale Correctness in Multimodal Large Language Models
2026-11-09 19:30:03Yanlin Chen, Tang Li, Xi PengAbstract
Multimodal large language models (MLLMs) are typically evaluated by whether they produce correct answers, but correctness alone does not reveal whether their outputs are supported by the right visual evidence. We introduce VIGOR, a benchmark for evaluating VIsually GrOunded Rationales in MLLMs. VIGOR represents visual rationales as explicit concepts paired with pixel-level groundings, covering multiple abstraction levels including low-level visual properties, intermediate structures, objects, parts and high-level motion, relations. To construct VIGOR at scale, we develop an automatic annotation framework that reuses existing dense supervision when available and generates missing concept groundings through proposal-based annotation followed by conservative multimodal verification. Using VIGOR, we evaluate whether MLLMs "look at what they say" by comparing model-derived visual evidence for each expressed concept against annotated ground-truth rationales. Our results show that current MLLMs exhibit limited visual rationale correctness and reveal distinct grounding failures across concept levels. VIGOR provides a benchmark and scalable data construction pipeline for studying whether MLLM outputs are supported by appropriate visual evidence. Code is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2611.13150
PDF
-
DOBB: Dynamic Oriented Bounding Boxes for Multi-Agent Collision Avoidance under State Uncertainty and Heterogeneous Dynamics
2026-11-09 19:23:34Pedro Antonio Alarcon Granadeno, Jane Cleland-HuangAbstract
Learning-based decentralized collision avoidance must remain reliable under state-estimation uncertainty and heterogeneous agent dynamics. Existing methods typically address these factors through training-domain variation or by exposing uncertainty and capability estimates to the policy at runtime. However, both leave the policy to infer how these quantities should alter the physical separation required for safe interaction, which can couple collision-avoidance behavior to relationships learned from the training distribution. We introduce the Dynamic Oriented Bounding Box (DOBB), an online geometric representation that maps the current state estimate, uncertainty, and agent-specific response characteristics into a dynamic, direction-dependent safety margin. We derive geometric features that jointly characterize the relative configuration and severity of interactions between agents' DOBBs, along with a reward function that preserves the physical interpretation of those interactions. Across four evaluation environments, DOBB achieves the lowest mean total failure rate of 2.6%. This performance persists under out-of-distribution shifts in actuation dynamics and state-estimation uncertainty, with collision-based failure remaining at or below 2.3% in every tested condition. We attribute this robustness to the geometric abstraction of the safety margin, which is less coupled to the specific uncertainty and actuation regimes encountered during training.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13142
PDF
-
Textual Response-Aware Guidance for Zero-Shot Adversarial Robustness of Vision-Language Models
2026-11-09 17:35:03Yubo Cui, Xianchao Guan, Zheng ZhangAbstract
Vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial attacks. Existing adversarial fine-tuning methods often use pre-trained model guidance to preserve image--text alignment while improving robustness. Our analysis of visual representation drift reveals complementary limitations of two representative forms of guidance. Matching visual features constrains all directions equally, providing broad coverage without semantic emphasis. Matching prediction distributions prioritizes semantically relevant directions, but remains limited by the candidate texts and prediction probabilities. These limitations can hinder preservation of pre-trained image--text relationships and degrade zero-shot performance. We therefore propose Textual Response-Aware Guidance (TRAG), which constrains visual representation drift using the pre-trained text encoder's responses to local variations in input embeddings. TRAG constructs anchor-level constraints from the response directions and magnitudes around semantic anchors, then aggregates them using pre-trained image--anchor relevance, yielding an image-adaptive constraint. Extensive experiments across architectures and tasks demonstrate state-of-the-art clean and robust performance. Further analysis shows that TRAG helps preserve pre-trained image--text relationships.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40309
PDF
-
SetPrint: Black-Box LLM Fingerprinting via Setwise Correspondence of Response Changes
2026-11-07 00:45:17Jinmo Han, Ju Yeon Kang, Jimin Hong, Sunghwan Ahn, Yonghyeon Jun, Nam Soo KimAbstract
Black-box LLM fingerprinting aims to determine whether a target model was derived from a source model when only the output responses to input queries are observable. One way to reveal this relationship is to perturb each query and observe the resulting responses of both models, yielding two corresponding sets of response variations. These sets provide two complementary sources of information: the relations among response changes within each set, and the correspondence of response changes between the two sets. Existing approaches, however, have not fully exploited both. We introduce \textbf{SetPrint}, a training-free method that jointly captures both within-set relations and between-set correspondence. SetPrint expresses each response change relative to the mean change of its own set, and then compares changes from the two models that were induced by the same perturbation. On LeaFBench, SetPrint consistently outperforms existing training-free black-box fingerprinting methods. Further analyses attribute these gains to both within-set relations and between-set correspondence.
Abstract (translated)
URL
https://arxiv.org/abs/2611.12950
PDF
-
GRAC: Graph-Based Retrieval-Augmented Captioning for Surgical Scene Description
2026-11-06 18:47:23Rochak Dhakal, Chen Zhao, Soup Cobb, Xin Qian, Xiaofeng Yang, Weihua ZhouAbstract
Purpose: Surgical operative reports support procedural documentation, surgical training, performance assessment, and workflow review. However, extracting meaningful information often requires extensive manual review and clinical expertise. Automated surgical scene descriptions could reduce this burden by leveraging recurring surgical activities and prior knowledge. Methods: We propose GRAC (Graph-Based Retrieval-Augmented Captioning), a framework that represents surgical scenes as graphs capturing relationships among instruments, actions, and anatomical structures. Given an input scene graph, GRAC learns to retrieve relevant graph-caption pairs from training data. It compares instrument-tissue interactions between retrieved examples and the input scene, using comparison features to condition retrieved-caption representations during generation. Results: On the EndoVis-18 benchmark, GRAC achieved a CIDEr-D of 5.88, compared with 4.23 for SGT and 3.36 for the strongest conventional Transformer baseline. Exact instrument-action-target triplet-set accuracy reached 52.6%, compared with 32.7% for SGT and 26.2% for the strongest conventional baseline. These results demonstrate improvements in language quality and factual agreement. On TORS, GRAC achieved a CIDEr-D of 5.06, compared with 3.80 for the strongest baseline. Conclusion: GRAC demonstrates that combining structured surgical scene representations with retrieved examples improves surgical scene captioning and produces more contextually meaningful descriptions.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09866
PDF
-
SURE:Spatiotemporal Uncertainty Representation for Efficient Vision-Language-Action Learning
2026-11-06 16:32:49Jingye Zhang, Choo Sin Wai, Dake Zhong, Zhifang Liu, Yuhong Zhang, Siyao Xiao, Guorui Song, Guocun Wang, Dongbin Zhang, Peng Jiao, Haoqian WangAbstract
Vision-language-action (VLA) policies have become a promising paradigm for end-to-end robot control, but their effectiveness still depends heavily on large volumes of demonstration data. In manipulation tasks, this dependence is compounded by structured spatiotemporal uncertainty in the action space: multiple nearby actions or trajectories may successfully solve the same task, while semantically equivalent demonstrations often unfold at different speeds. Standard pointwise supervision treats each demonstrated action as an exact target, imposing an unnecessary learning burden under such uncertainty. We present SURE, a data-efficient VLA training framework that explicitly models both spatial and temporal uncertainty. SURE augments a VLA backbone with a lightweight transposed-convolutional probabilistic action decoder that captures spatial uncertainty through local correlations among neighboring action bins. It further introduces Soft-DTW alignment supervision to accommodate local timing variations between predicted and demonstrated action chunks. Together, these two components reduce sensitivity to demonstrator-specific poses and execution timing, enabling more data-efficient action learning. We evaluate SURE on LIBERO, RoboTwin 2.0, and real-world manipulation tasks. Even with only 10% of the demonstration data or 20% of the training steps, SURE achieves manipulation success rates that match or surpass baseline VLAs.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09684
PDF
-
Dual Architecture Fusion Vehicle Lidar 3D Target Detection
2026-11-06 16:13:58Muyun Li, Weizheng Jin, Yuan SunAbstract
In this paper, a 3D backbone network (SpconvTransformer) based on the fusion of convolutional architecture branch and Transformer architecture branch is proposed. The convolution branch uses 3D sparse convolution and submanifold convolution to learn local voxel features and semantic information, and the Transformer branch uses the self-attention mechanism to model the remote relationship between voxels, uses the broad receptive field to capture rich context information, and complementing the advantages of the two architectures by fusing the local features extracted from the two branches and the global features solves the problem of limited receptive fields of 3D convolutional neural networks. The experimental results show that the average accuracy of SpconvTransformer in 3D object detection and bird's-eye view detection tasks reaches 81.45% and 88.09%, respectively, and the average directional similarity reaches 91.10%, which is significantly better than other existing algorithms.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09664
PDF
-
Multimodal Training with Knowledge Traction for Video Anomaly Detection
2026-11-06 14:50:13Xiao TanAbstract
The task of weakly supervised video anomaly detection is challenging. Existing approaches mainly model video frame features and determine whether anomalies are present based on their magnitudes. In this work, we propose a novel method that incorporates external knowledge into training to improve model performance, robustness, and generalization. We leverage textual prompts and a large language model (LLM) to establish prior information for the specific task, and employ dictionary learning to normalize and compress this information. Moreover, during experiments, we observed inconsistencies in the textual descriptions extracted from similar video frames by image caption models. To address this, we devise a method that leverages an LLM and auxiliary information to ensure consistency in the textual descriptions of similar frames within a video. Finally, we introduce a feature processing approach that incorporates prior knowledge and cross-modal attention mechanisms. This approach learns the relationships and characteristics among different modalities to construct more accurate and reliable feature representations, thereby improving the accuracy and stability of downstream tasks. Experimental results demonstrate that our method surpasses other state-of-the-art approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09536
PDF
-
Embedding Predictive Adaptation and Refinement for Multi-Modal Industrial Anomaly Detection
2026-11-06 14:36:31Jaeho Cho, Jinsik Bang, Taehwan KimAbstract
Industrial Anomaly Detection (IAD) has evolved from 2D image-based approaches to multi-modal methods that leverage the complementary nature of RGB images and 3D point clouds. Among these, memory bank-based methods, which identify anomalies by the discrepancy between each query patch feature and its nearest normal prototype, have proven particularly effective. However, two limitations remain: (i) employing frozen pretrained encoders yields insufficient discrimination between normal and anomalous features due to the domain gap, while existing contrastive learning-based adaptation struggles to capture the spatial relationships required for precise localization; and (ii) pixel-level anomaly maps interpolated from patch-level distance scores remain coarse, lacking fine-grained detail. To address these limitations, we propose EPAR (Embedding Predictive Adaptation and Refinement). We adapt encoders by predicting the embeddings of masked regions to capture spatial relationships, together with patch-level Variance-Invariance-Covariance (VIC) regularization, resolving the poor discriminability between normal and anomalous features caused by the domain gap. We further propose a Noise Suppression Network that refines coarse maps by learning the relational discrepancy between each patch feature and its nearest normal prototype, rather than the anomaly's appearance. This relational signal remains valid for unseen real defects, despite being learned from synthetic anomalies. EPAR demonstrates strong practical applicability, excelling in few-shot settings and improving AUPRO@1% on MVTec 3D-AD and Eyecandies by +1.8% and +1.9%, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09521
PDF
-
Cognitive Maps in Large Language Models
2026-11-06 14:33:05Albert Qin, Jonathan D. Cohen, Gautam ReddyAbstract
It has long been proposed that animals construct cognitive maps to support flexible behavior in novel environments. We tested whether large language models form analogous internal representations using relational reasoning tasks and causal "mosaic" experiments. Models beyond the ten-billion-parameter scale inferred unstated relationships and generalized to synthetic entity names. Across models and tasks, models formed abstract representations of relational structure, additively combining them with representations of entity identity. Relationships were primarily stored as pairwise links and composed retrospectively, rather than prospectively encoded in a global coordinate system. A sparse, distributed set of key-value pairs mediated binding; perturbing them implanted "false memories" that produced predictable behavioral changes. Our findings reveal a conserved organization analogous to a cognitive map supporting flexible and systematic reasoning in language models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.25596
PDF
-
Tracing Psychometric Inference in Large Language Models
2026-11-06 14:29:19Chih-Hao Hsu, Feng-Chun B. Chou, Pin-Hao A. ChenAbstract
Do large language models represent psychological constructs internally, or do they only generate outputs that resemble psychometric structure? We address this question using a cross-persona paradigm across 14 model variants from two families (Llama 3 and Qwen 2.5, 0.5B-14B, base and instruct). Given responses on one psychological scale from real individuals (N = 272 Taiwanese university students), models predict responses on six other scales. At the behavioral level, larger variants reproduce and amplify human cross-scale correlations; amplification persists after correcting the seven-scale human correlations for measurement attenuation. We then examine whether this structure is reflected internally. Contrastive direction analysis finds geometry aligned with the human matrix in larger instruct variants, but little alignment in base variants under this assay. Across models, geometry strength is associated with behavioral amplification (r = 0.68, p = 0.008; partial r = 0.69 controlling for log size). To relate internal structure to output behavior, a matched activation-probing paradigm shows that probe slopes vary less than behavioral slopes (1.38-1.77 vs 0.52-1.53). A synthetic control shows that ridge probing can inflate these slopes; after subtracting a baseline based on a reliability proxy from another analysis, adjusted slopes remain associated with behavior (r = 0.88). We term the measured probe-behavior gap readout attenuation. These results establish decodability and geometric alignment under the tested assays, without showing that the measured directions mediate the cross-persona answers.
Abstract (translated)
URL
https://arxiv.org/abs/2611.12937
PDF
-
BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression
2026-11-06 14:23:34Gon\c{c}alo Gomes, Bruno Martins, Chrysoula ZervaAbstract
Reliable uncertainty estimation is important for deploying evaluation metrics in real-world settings, where both input ambiguity and domain shifts are common. In this work, we propose an uncertainty-aware extension of the BEiTScore image captioning metric, producing conformally calibrated confidence intervals alongside alignment scores. Our approach models predictive distributions over human judgments, enabling both accurate scoring and principled uncertainty quantification in a single forward pass. We evaluate our BEiTScore++ metric across multiple benchmarks with human-annotated ratings, showing that it preserves the ranking correlation of BEiTScore, while producing intervals whose width tracks the prediction error more closely than Monte Carlo dropout on most benchmarks. The estimated uncertainty also grows under image degradation and on out-of-domain artwork images, making BEiTScore++ a practical tool for uncertainty-aware evaluation of image-caption alignment.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09505
PDF
-
LEMMO: A Large Electromagnetic Model leveraging Pretrained LLMs for Million-Sample Signal Understanding
2026-11-06 13:56:33Mingkai Li, Jiajun Wu, Yihan Mao, Zilin Sang, Taosong Yu, Yuan Ma, Minghe Liu, Qianqian Yang, Zhiguo ShiAbstract
Large language models have expanded beyond text to vision, audio, and other modalities, but understanding raw electromagnetic (EM) signals remains challenging. Wideband recordings can contain millions of samples, whereas existing waveform-based EM models are primarily evaluated on short in-phase and quadrature (IQ) segments, leaving long-recording understanding and detailed description insufficiently explored. We introduce LEMMO, a large EM model for instruction-driven recognition and description of long raw IQ recordings. LEMMO combines a linear-attention EM encoder with anti-aliased temporal resampling to process up to eight million complex samples. Its EM-text interaction module conditions learnable queries on instructions before retrieving signal evidence. Compact queries support recognition, while structured queries with auxiliary factual supervision organize scene-level properties, signal attributes, and cross-signal relationships for detailed description. We also construct and release a unified 1.38-TB corpus of real-world and synthetic EM signals, including LEMMO-ShortQA and LEMMO-LongDesc. Compared with MERLIN-LoRA, LEMMO improves mean EM-Bench perception accuracy by 15.77 %, mean strategy-generation ROUGE-L F1 by 4.38 points, and mean LEMMO-ShortQA accuracy by 14.31 %. It also improves categorical and numerical fact F1 on both LEMMO-LongDesc tasks while preserving its language backbone's MMLU performance. Our code and datasets are available at this https URL and this https URL, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09476
PDF
-
A Spiking Neural Model of the Mental Lexicon: Representations, Similarity Structure, and Associative Retrieval in Perception and Production
Abstract
A neural account of lexical access requires an explicit distinction between the structure of lexical representations, the associations linking representational levels, and the activity generated during retrieval. This paper specifies a spiking neural implementation of the mental lexicon within the Neural Engineering Framework and Semantic Pointer Architecture. Conceptual and phonological form representations are constructed recursively from relational graphs, whereas lemma representations provide independent lexical identities. The implementation contains 613 lexical entries and supports two directed processing pathways: perception maps a phonological form to its associated concept via a lemma, whereas production maps a concept to its associated phonological form via a lemma. Each pathway combines two associative-memory variants, winner-take-all (WTA) selection (competition) and thresholded transfer, and uses 199,400 leaky integrate-and-fire neurons. We formalize within-level similarity, cross-level associative retrieval, and the interpretation of decoded activity. Simulations show successful retrieval of eight selected words from the lexicon in both processing directions, with retrieval evaluated against all 613 lexical entries. These simulations use complete phonological forms as input for perception and complete concepts as input for production, illustrating lexical retrieval through the corresponding processing pathways. This paper provides a transparent description of lexical representations and neural retrieval mechanisms, supported by accessible code, lexical data, and online simulation documentation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09402
PDF
-
Syn2DRE: Synergistic Dual Teacher-Student Framework for Document-level Relation Extraction
2026-11-06 11:40:53Khai Phan Tran, Xue LiAbstract
Document-level Relation Extraction (DocRE) aims to identify relations between entities across a document but typically relies on costly large-scale annotations. While pseudo-labelling enables the use of low-quality data, existing methods often suffer from inefficiency and confirmation bias. To address these challenges, we propose Syn2DRE, a semi-supervised framework that combines self-supervised learning with cross-supervision in a lightweight teacher-student architecture to produce more reliable pseudo-labels. Additionally, we introduce a unified end-to-end training strategy to further improve efficiency of the framework. Experiments on multiple benchmarks show that Syn2DRE consistently outperforms prior state-of-the-art semi-supervised DocRE methods.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09342
PDF
-
ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective
2026-11-06 11:17:58Chaoran Li, Yukun Li, Zeyuan Zhao, Shao Zhang, Xihuai Wang, Ying WenAbstract
Foundation models are increasingly deployed as agentic systems that perceive context and act autonomously, raising the need to evaluate their moral behavior as active decision-makers. Existing benchmarks, however, largely ask models to judge human actions from third-person textual vignettes, leaving untested how models behave when they themselves become the acting agent. We introduce ABHBench, a multimodal benchmark built from Detroit: Become Human, an interactive narrative game, to evaluate how foundation models make moral decisions in first-person human-android dilemmas. ABHBench places foundation models in branching narrative scenarios with visual observations, dialogue, memory, and action choices. Inspired by Asimov's Three Laws of Robotics, our framework measures Harmlessness, Obedience, and Self-preservation to capture the core tensions in human-AI relations, along with Autonomy, Stability, and Certainty to assess decision-making patterns. Across 12 foundation models, we find that moral behavior changes substantially under situated agentic context: 75% of models shift significantly between a text-only abstraction and the matched multimodal DBH scenario, and reasoning-enhanced models show no monotonic gains in consistency or human-oriented behavior. These results highlight the necessity of evaluating moral behavior in situated agentic contexts rather than relying on third-person judgment alone.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09326
PDF
-
T2I Models Rarely Invert Negation but Often Fail to Suppress Negated Concepts: Benchmarking Negation Suppression in Text-to-Image Generation
2026-11-06 10:56:01Akansha Gautam, Aparna Bharati, Mayank Vatsa, Richa SinghAbstract
Text-to-image diffusion models often fail to suppress explicitly negated concepts, such as a lamp for "a desk without a lamp." We introduce T2I-NSI, a benchmark and metric for measuring negation sensitivity in text-to-image generation. It pairs each negated prompt with a canonical positive counterpart and factorizes negation by linguistic form (lexical/semantic, morphological, syntactic) and target type (objects, attributes, relations, compositions, and nested cases). The benchmark contains 759,869 paired prompt atoms over a 5,082-object catalog, with 916,272 images (911,982 open-weights, 4,290 closed-source), scored by a Basic CLIP estimator and a Robust ensemble of CLIP, VQA and open-vocabulary detection. Negation sensitivity is low: open-weights generators score NSI <= 0.038, while GPT-Image-1.5 and Gemini-2.5-Flash-Image reach about 0.09. The dominant failure is under-suppression rather than misdirection. Inverse interpretation is essentially absent (0.00% across over 450K atom-model evaluations), whereas models render the concept under both prompts on 8-19% of atoms and only partly suppress it on a further 9-25%; most remaining atoms are too weakly rendered to label. A blinded human study (420 atoms, nine annotators) corroborates the near-absence of inversion and the high persistence rate, and a matched-prompt comparison shows the open-versus-closed gap (~3.5x) is not a prompt-generator artifact. Code and data: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2611.09304
PDF
-
MDF++: Visuo-Tactile World Action Model with End-to-end Representation Learning
2026-11-06 10:47:23Zixuan Huang, Jinhao Yu, Zachary Charlick, Dmitry BerensonAbstract
Recently, world-action models (WAMs) have emerged as a powerful framework for robot manipulation. By jointly modeling action generation and future observation prediction, WAMs can act and anticipate the outcomes of the actions. However, existing WAMs typically rely on frozen pretrained encoders trained with reconstruction, which may not produce representations well suited for robot control. In this paper, we tackle the problem of learning physicallygrounded, control-relevant representations for WAMs. We propose MDF++, a visuo-tactile world-action model that learns latent representations of multisensory observations end-to-end with a diffusion backbone. While naive joint training can lead to feature collapse, MDF++ introduces a multi-task learning strategy that leverages cross-modal correlations to learn task-relevant representations. We evaluate MDF++ on a suite of contact-rich manipulation tasks, including realworld bolt screwing and nut mating, and show that it outperforms WAMs built on frozen pretrained representations by up to 50%. Additional videos are available on our website: this http URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09293
PDF
-
Bootstrap Your Own AV-Proxies: Adaptive Contrastive and Prototype Learning for Audio-Visual Segmentation
2026-11-06 09:14:18Junbo Zhang, Hang Su, Zhaofan Li, Hang Dong, Chao SunAbstract
Audio-Visual Segmentation (AVS) aims to accurately segment sounding objects in video frames by leveraging audio-visual correspondence cues. However, it remains challenging due to the intrinsic semantic incompleteness within a single modality and the semantic gap between audio and visual representations. Traditional feature-fusion decoding approaches struggle to suppress fusion noise effectively, while recent methods that incorporate data-dependent priors often increase the complexity of modeling audio-visual correlations, leading to poor cross-domain generalization. To address these issues, we propose a novel adaptive contrastive and prototype learning framework, BYOAVP, for AVS. Specifically, we design a Self-Supervised Audio Enhancement (SSAE) module that introduces contrastive learning to adaptively align audio representations with gradient-blocked visual embeddings, thus narrowing the semantic gap between modalities. Furthermore, a Dynamic Prototype Constraint (DPC) module is developed to refine pixel-wise category perception via momentum-based prototype updating, while enhancing localization of sounding regions through cross-modal interaction. Extensive experiments demonstrate that our method achieves SOTA performance across two AVS benchmarks and six sub-tasks, exhibiting strong robustness and generalization ability.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09191
PDF
-
AdaAlloc: Adaptive Visual Token Allocation for Long-Video Question Answering
2026-11-06 07:21:49Joungbin An, Kristen GraumanAbstract
Long-video question answering forces multimodal large language models to reason under strict visual-token budgets, creating a tradeoff between broad temporal coverage and fine-grained spatial detail. Uniform sampling preserves coverage but often obscures decisive local cues, while caption-based or frame-similarity retrieval operates over lossy proxies that can miss motion, state changes, and before-after relations. We recast long-video reasoning as a visual-token allocation problem: given a fixed budget, decide how much to spend on global context versus high-resolution local evidence, and where in the video to draw that local evidence from. We introduce AdaAlloc, a training-free inference framework that adaptively allocates visual tokens between a global video overview and localized visual detail. AdaAlloc first plans a global/local allocation policy, then uses temporal grounding to locate candidate evidence segments and refines them into a compact temporal memory. The selected policy controls both frame sampling density and resolution, combining sparse, lower-resolution global frames with denser, higher-resolution local frames drawn from the refined memory. The final answerer reasons over the allocated global context and refined local evidence. Across LVBench, MLVU, VideoMME, and LongVideoBench, AdaAlloc improves over budget-matched uniform sampling by up to 10.5 percentage points and outperforms the compared frame-selection and agentic methods on their reported benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09092
PDF
