VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning

• URL: http://arxiv.org/abs/2509.25151v1
• Date: Mon, 29 Sep 2025 17:54:04 GMT
• Title: VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning
• Abstract summary: VideoAnchor is a plug-and-play module that leverages subspace affinities to reinforce visual cues across frames without retraining.<n>We show consistent performance gains on benchmarks with InternVL2-8B and Q2.5VL-72B.<n>Our codes will be made public at https://github.com/feufhd/VideoAnchor.
• Score: 69.64660280965971
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language alignment, yet they remain limited in visual-spatial reasoning. We first identify that this limitation arises from the attention mechanism: visual tokens are overshadowed by language tokens, preventing the model from consistently recognizing the same visual cues across frames. To address this challenge, we draw a novel connection between the self-expressiveness property in sparse subspace clustering and the attention mechanism in Transformers. Building on this insight, we propose VideoAnchor, a plug-and-play module that leverages subspace affinities to reinforce visual cues across frames without retraining, effectively anchoring attention to shared visual structures. Extensive experiments across benchmarks and backbone models show consistent performance gains -- $e.g.$, 3.2% and 4.6% improvements on VSI-Bench and Video-MME (spatial-related tasks) with InternVL2-8B and Qwen2.5VL-72B -- while qualitative analyses demonstrate more coherent subspace partitions and stronger visual grounding. Our codes will be made public available at https://github.com/feufhd/VideoAnchor.

Related papers

• VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context [47.466197471764104]
  We propose **VisReflect**, a framework that improves fine-grained perception in long visual contexts through latent visual reflection.<n>Our method consistently improves over strong baselines, achieving gains of 4.1% on image benchmarks and 1.8% on video benchmarks.<n>Compared with zooming-based methods, our model achieves comparable performance while reducing inference time by roughly 44% on video understanding.
  arXiv  Detail & Related papers  (2026-06-29T13:30:17Z)
• Reasoning as Intersection: Consensus-Frame Alignment for Visual Focus in Video-MLLMs [81.04673240949074]
  Reinforcement learning has improved the reasoning ability of large language models.<n>Applying outcome-only rewards to video multimodal large language models provides limited guidance on which visual evidence should support the answer.<n>We introduce Consensus Frame GRPO, a temporal-annotation-free process-level reward framework for evidence-aware video reasoning.
  arXiv  Detail & Related papers  (2026-06-16T19:42:54Z)
• Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification [80.62512020268626]
  UniAR is a unified autoregressive framework where a single visual tokenizer serves as the key bridge between understanding and generation.<n>UniAR adapts a pretrained vision encoder with multi-level feature fusion and a lookup-free bitwise quantization scheme.<n>A diffusion-based visual decoder operates on discrete visual tokens to decode high-fidelity images.
  arXiv  Detail & Related papers  (2026-06-16T17:59:22Z)
• Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models [58.9387276447485]
  Vision Inference Former (VIF) is a lightweight architectural module that establishes a bridge between pure visual representations and the model's output space.<n>We conduct experiments on 14 benchmark tasks covering general reasoning, OCR, table understanding, vision-centric evaluation, and hallucination.
  arXiv  Detail & Related papers  (2026-05-18T10:04:22Z)
• EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models [39.77362541405281]
  EPIC-Bench is a grounding benchmark for large vision-language models (VLMs)<n>It systematically evaluates the visual perceptual capabilities of VLMs in real-world embodied environments.
  arXiv  Detail & Related papers  (2026-05-16T16:38:51Z)
• PatchCue: Enhancing Vision-Language Model Reasoning with Patch-Based Visual Cues [28.522392005763873]
  We propose PatchCue, a novel patch-based visual cue paradigm designed to significantly enhance the visual reasoning capabilities of Vision-Language Models (VLMs)<n>By partitioning images into patches and representing cues at the patch level, PatchCue aligns better with human perceptual habits and leverages the patch-tokenized input of modern VLMs.<n>Our results show that patch-level cues outperform both pixel-level bounding boxes and point-based cues, providing a more effective and cognitively aligned visual reasoning paradigm.
  arXiv  Detail & Related papers  (2026-03-06T03:44:27Z)
• EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence [10.889641815961133]
  spatial intelligence approaches typically attach 3D cues to 2D reasoning pipelines or MLLMs with black-box reconstruction modules.<n>We present EagleVision, a framework for progressive spatial cognition through macro perception and micro verification.
  arXiv  Detail & Related papers  (2025-12-17T07:51:36Z)
• Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding [43.63398524449102]
  Humans perceive complex scenes efficiently by dynamically scanning and focusing on salient regions in a sequential "blink-like" process.<n>We propose Blink, a dynamic visual token resolution framework that emulates the human-inspired process within a single forward pass.<n>Blink balances broad exploration and fine-grained focus, thereby enhancing visual perception adaptively and efficiently.
  arXiv  Detail & Related papers  (2025-12-11T11:27:25Z)
• Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens [54.18057944158818]
  Chain-of-Visual-Thought (COVT) is a framework that enables Vision-Language Models (VLMs) to reason through continuous visual tokens.<n>Within a small budget of roughly 20 tokens, COVT distills knowledge from lightweight vision experts.<n>During training, the VLM with COVT autoregressively predicts visual tokens to reconstruct dense supervision signals.
  arXiv  Detail & Related papers  (2025-11-24T18:55:19Z)
• Complementary and Contrastive Learning for Audio-Visual Segmentation [74.11434759171199]
  We present Complementary and Contrastive Transformer (CCFormer), a novel framework adept at processing both local and global information.<n>Our method sets new state-of-the-art benchmarks across the S4, MS3 and AVSS datasets.
  arXiv  Detail & Related papers  (2025-10-11T06:36:59Z)
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)
• DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs [28.998923104606614]
  DisCo is a visual encapsulation method designed to yield semantically distinct and temporally coherent visual tokens for video MLLMs.<n>DisCo remarkably outperforms previous state-of-the-art methods across a variety of video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-07-14T14:05:19Z)
• FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation [55.01077993490845]
  Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling.<n>We introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework.
  arXiv  Detail & Related papers  (2025-06-20T07:46:40Z)
• Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models [18.02840698188587]
  We propose a novel kernel-based method to align CLIP's visual representation with that of DINOv2.<n>Our image-only alignment fine-tuning exhibits significant improvements in zero-shot object recognition, fine-grained spatial reasoning.
  arXiv  Detail & Related papers  (2025-06-03T07:44:43Z)
• QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension [86.0749609778104]
  We propose QuoTA, an ante-hoc training-free modular that extends existing large video-language models.<n>QuoTA strategically allocates frame-level importance scores based on query relevance.<n>We decouple the query through Chain-of-Thoughts reasoning to facilitate more precise LVLM-based frame importance scoring.
  arXiv  Detail & Related papers  (2025-03-11T17:59:57Z)
• The Devil is in Temporal Token: High Quality Video Reasoning Segmentation [68.33080352141653]
  Methods for Video Reasoning rely heavily on a single special token to represent the object in the video.<n>We propose VRS-HQ, an end-to-end video reasoning segmentation approach.<n>Our results highlight the strong temporal reasoning and segmentation capabilities of our method.
  arXiv  Detail & Related papers  (2025-01-15T03:17:24Z)
• Redundancy-aware Transformer for Video Question Answering [71.98116071679065]
  We propose a novel transformer-based architecture, that aims to model VideoQA in a redundancy-aware manner. To address the neighboring-frame redundancy, we introduce a video encoder structure that emphasizes the object-level change in neighboring frames. As for the cross-modal redundancy, we equip our fusion module with a novel adaptive sampling, which explicitly differentiates the vision-language interactions.
  arXiv  Detail & Related papers  (2023-08-07T03:16:24Z)
• Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives [30.666823939595627]
  This paper reconsiders the multi-modal alignment problem in VideoQA from feature and sample perspectives. We adopt a heterogeneous graph architecture and design a hierarchical framework to align both trajectory-level and frame-level visual feature with language feature. Our method outperforms all the state-of-the-art models on the challenging NExT-QA benchmark.
  arXiv  Detail & Related papers  (2022-04-25T10:42:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.