Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models

• URL: http://arxiv.org/abs/2512.06281v1
• Date: Sat, 06 Dec 2025 04:20:13 GMT
• Title: Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models
• Authors: Hengzhuang Li, Xinsong Zhang, Qiming Peng, Bin Luo, Han Hu, Dengyang Jiang, Han-Jia Ye, Teng Zhang, Hai Jin,
• Abstract summary: 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.
• Score: 58.91911788912665
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in multimodal tasks. Despite their impressive performance, MLLMs suffer from the modality imbalance issue, where visual information is often underutilized compared to textual representations in deeper layers, leading to degraded visual performance or hallucinations. This issue stems from the predominant reliance on next-text-token-prediction during training, which fails to provide direct visual supervisory signals, resulting in progressive homogenization of visual representations throughout the layers. To this end, we propose Latent Visual Reconstruction (LaVer), a novel training framework that facilitates MLLMs in learning more discriminative visual representations via masked image modeling in the joint latent semantic space of LLM. Our method offers direct visual activation to MLLMs, which exhibit increased visual attention allocation, indicating enhanced utilization of visual information. Extensive experiments across diverse benchmarks prove the superiority of our approach in various scenarios, especially those requiring dense visual capabilities. Code of LaVer is available at https://github.com/Fir-lat/LaVer.

Related papers

• Visual Representation Alignment for Multimodal Large Language Models [38.319869213758686]
  Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks.<n>But they remain limited in vision-centric tasks such as object counting or spatial reasoning.<n>We present VIsual Representation ALignment (VIRAL), a simple yet effective regularization strategy that aligns the internal visual representations of MLLMs with those of pre-trained vision foundation models.
  arXiv  Detail & Related papers  (2025-09-09T17:59:14Z)
• SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding [5.976839106353883]
  SECOND: Selective and Contrastive Decoding is a novel approach that enables Vision-Language Models to leverage multi-scale visual information with an object-centric manner.<n> SECOND significantly reduces perceptual hallucinations and outperforms a wide range of benchmarks.
  arXiv  Detail & Related papers  (2025-06-10T02:55:38Z)
• Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference [28.24397677839652]
  Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models.<n>How MLLMs process and utilize visual information remains unclear.<n>We propose Hierarchical Modality-Aware Pruning (HiMAP), a plug-and-play inference acceleration method that dynamically prunes image tokens at specific layers, reducing computational costs by approximately 65% without sacrificing performance.
  arXiv  Detail & Related papers  (2025-03-17T12:31:23Z)
• 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)
• EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models [80.00303150568696]
  We propose a novel Multimodal Large Language Models (MLLM) that empowers comprehension of arbitrary referring visual prompts with less training efforts than existing approaches. Our approach embeds referring visual prompts as spatial concepts conveying specific spatial areas comprehensible to the MLLM. We also propose a Geometry-Agnostic Learning paradigm (GAL) to further disentangle the MLLM's region-level comprehension with the specific formats of referring visual prompts.
  arXiv  Detail & Related papers  (2024-09-25T08:22:00Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• Visualization Literacy of Multimodal Large Language Models: A Comparative Study [12.367399155606162]
  multimodal large language models (MLLMs) combine the inherent power of large language models (LLMs) with the renewed capabilities to reason about the multimodal context. Many recent works in visualization have demonstrated MLLMs' capability to understand and interpret visualization results and explain the content of the visualization to users in natural language. In this work, we aim to fill the gap by utilizing the concept of visualization literacy to evaluate MLLMs.
  arXiv  Detail & Related papers  (2024-06-24T17:52:16Z)
• Towards Semantic Equivalence of Tokenization in Multimodal LLM [149.11720372278273]
  Vision tokenization is essential for semantic alignment between vision and language.<n>This paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok)<n>SeTok groups visual features into semantic units via a dynamic clustering algorithm.<n>The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features.
  arXiv  Detail & Related papers  (2024-06-07T17:55:43Z)
• Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models [121.83413400686139]
  This paper proposes to improve the visual perception ability of MLLMs through a mixture-of-experts knowledge enhancement mechanism. We introduce a novel method that incorporates multi-task encoders and visual tools into the existing MLLMs training and inference pipeline.
  arXiv  Detail & Related papers  (2024-01-06T02:02:34Z)
• From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models [36.41816380074965]
  We investigate the effectiveness of different vision encoders within Large Language Models (MLLMs) Our findings reveal that the shallow layer features of CLIP offer particular advantages for fine-grained tasks such as grounding and region understanding. We propose a simple yet effective feature merging strategy, named COMM, that integrates CLIP and DINO with Multi-level features Merging.
  arXiv  Detail & Related papers  (2023-10-13T02:41:55Z)

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.