Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models

• URL: http://arxiv.org/abs/2606.30168v1
• Date: Mon, 29 Jun 2026 11:44:09 GMT
• Title: Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models
• Abstract summary: Multimodal large language models (MLLMs) often fail in fine-grained visual reasoning.<n>We propose LatEnt Noise maSk (Lens), a question-conditioned visual evidence purification framework.<n>Lens scores which visual tokens support the current question and preserve them during decoding.
• Score: 56.11961584000622
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) often fail in fine-grained visual reasoning, as question-relevant visual cues are diluted by dense and redundant image tokens. Recent multimodal reasoning methods usually extend chain-of-thought from language models into visual or latent spaces, seeking to add intermediate reasoning states while overlooking the negative impact of redundant visual tokens. We propose LatEnt Noise maSk (Lens), a question-conditioned visual evidence purification framework that empowers MLLMs to reason with cleaner visual cues in latent space. Lens introduces a lightweight Lens Evidence Token (LET) to score which visual tokens support the current question and preserve them during decoding. Guided by the LET scores, it injects adaptive latent noise into low-relevance tokens, softly suppressing distractors without changing the model backbone or token sequence. With only one temporary learnable control token and a lightweight noise generator, Lens adds minimal overhead while improving the base MLLM by 2.4-6.4 points on most VQA datasets and by 4.1-6.4 points on grounding tasks. These results show that multimodal reasoning can benefit more directly from cleaner question-relevant visual evidence than from simply extending the reasoning trace.

Related papers

• VisLens: Single-Pass Interpretable Visual Search for Multimodal LLMs [50.62479086957651]
  We propose emphVisLens (Visual Focus via Logit Lens), a Visual Search method built on the logit lens.<n>VisLens matches or exceeds prior baselines while delivering a substantial latency advantage.
  arXiv  Detail & Related papers  (2026-08-31T12:43:42Z)
• What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models [9.530137749236617]
  Multimodal large language models (MLLMs) project visual tokens into the embedding space of language models.<n>We introduce a two-fold analytical framework featuring a novel probing tool, $textLenEmbeds$, to conduct a fine-grained analysis.<n>We uncover a pronounced semantic sparsity at the input level: visual tokens consistently partition into sink, dead, and alive categories.
  arXiv  Detail & Related papers  (2026-02-28T07:13:36Z)
• Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation [51.743225614196774]
  Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language reasoning.<n>They remain vulnerable to hallucination, where generated content deviates from visual evidence.<n>Recent vision enhancement methods attempt to address this issue by reinforcing visual tokens during decoding.<n>We propose Adaptive Visual Reinforcement (AIR), a training-free framework for MLLMs.
  arXiv  Detail & Related papers  (2026-02-27T14:18:51Z)
• Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models [58.91911788912665]
  We propose Latent Visual Reconstruction (LaVer), a novel training framework that facilitates MLLMs in learning more discrimi visual representations.<n>Our method offers direct visual activation to MLLMs, which exhibit increased visual attention allocation, indicating enhanced utilization of visual information.
  arXiv  Detail & Related papers  (2025-12-06T04:20:13Z)
• Latent Visual Reasoning [40.347006722601975]
  We introduce Latent Visual Reasoning (LVR), a new paradigm that enables autoregressive reasoning directly in the visual embedding space.<n>We show that LVR substantially improves fine-grained visual understanding and perception, achieving 71.67% on MMVP compared to 66.67% with Qwen2.5-VL.
  arXiv  Detail & Related papers  (2025-09-29T03:52:01Z)
• Token Activation Map to Visually Explain Multimodal LLMs [23.774995444587667]
  We propose an estimated causal inference method to mitigate the interference of context to achieve high-quality MLLM explanation.<n>We term this method Token Activation Map (TAM) to highlight the consideration of interactions between tokens.<n>Our TAM method significantly outperforms existing SoTA methods, showcasing high-quality visualization results.
  arXiv  Detail & Related papers  (2025-06-29T14:50:45Z)
• Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning [53.790502697674754]
  We propose Take-along Visual Conditioning (TVC), a strategy that shifts image input to critical reasoning stages.<n>TVC helps the model retain attention to the visual components throughout the reasoning.<n>Our approach achieves state-of-the-art performance on average across five mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-03-17T16:45:12Z)
• What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph [15.364317811275344]
  We propose a graph-based method towards training-free visual token pruning, termed G-Prune.<n>G-Prune regards visual tokens as nodes, and construct their connections based on their semantic similarities.<n>Experiment results show that G-Prune can greatly reduce computation overhead while retaining high performance on both coarse- and fine-grained tasks.
  arXiv  Detail & Related papers  (2025-01-04T12:14:42Z)
• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings [66.04061083611863]
  Excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation.<n>We propose a simple yet effective method to improve the efficiency of MLLMs, termed dynamic visual-token exit (DyVTE)<n>DyVTE uses lightweight hyper-networks to perceive the text token status and decide the removal of all visual tokens after a certain layer.
  arXiv  Detail & Related papers  (2024-11-29T11:24:23Z)

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.