Cover Image

Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yin, Hao, Si, Guangzong, Wang, Zilei
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?
by: Yin, Hao, et al.
Published: (2025)

ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models
by: Yin, Hao, et al.
Published: (2025)

Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder
by: Wang, Jingchao, et al.
Published: (2025)

AdaCodec: A Predictive Visual Code for Video MLLMs
by: Hou, Haowen, et al.
Published: (2026)

Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs
by: Si, Guangzong, et al.
Published: (2025)

Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localization
by: Chen, Yuqi, et al.
Published: (2026)

Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
by: Zhang, Yi, et al.
Published: (2025)

VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
by: Jiang, Pengfei, et al.
Published: (2025)

Unlocking the Forgery Detection Potential of Vanilla MLLMs: A Novel Training-Free Pipeline
by: Zuo, Rui, et al.
Published: (2025)

VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs
by: Li, Qiaoru, et al.
Published: (2026)

CrystaL: Spontaneous Emergence of Visual Latents in MLLMs
by: Zhang, Yang, et al.
Published: (2026)

StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs
by: Che, Chang, et al.
Published: (2026)

IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation
by: Jiang, Yankai, et al.
Published: (2026)

Towards Faithful Reasoning in Comics for Small MLLMs
by: Feng, Chengcheng, et al.
Published: (2026)

IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs
by: Tan, Yifan, et al.
Published: (2026)

Towards Unified Surgical Scene Understanding:Bridging Reasoning and Grounding via MLLMs
by: Huang, Jincai, et al.
Published: (2026)

SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation
by: Pei, Yuhan, et al.
Published: (2024)

Faster Inference of Integer SWIN Transformer by Removing the GELU Activation
by: Tayaranian, Mohammadreza, et al.
Published: (2024)

Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
by: Liu, Xiaolin, et al.
Published: (2026)

Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
by: Li, Yuanshuai, et al.
Published: (2025)

When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs
by: Cao, Fanpu, et al.
Published: (2026)

Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs
by: Ou, Siqu, et al.
Published: (2026)

EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations
by: Heng, Yongrui, et al.
Published: (2026)

Dense Connector for MLLMs
by: Yao, Huanjin, et al.
Published: (2024)

The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
by: Yuan, Shuai, et al.
Published: (2024)

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
by: Huang, Zhe, et al.
Published: (2025)

S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance
by: Xu, Beining, et al.
Published: (2025)

I Spy With My Model's Eye: Visual Search as a Behavioural Test for MLLMs
by: Burden, John, et al.
Published: (2025)

How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images
by: Liu, Guimeng, et al.
Published: (2026)

RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
by: Liu, Ziyu, et al.
Published: (2024)

Cube Bench: A Benchmark for Spatial Visual Reasoning in MLLMs
by: Anand, Dhruv, et al.
Published: (2025)

Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning
by: Guo, Zirun, et al.
Published: (2025)

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension
by: Ouyang, Kun, et al.
Published: (2024)

StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning
by: He, Xixiang, et al.
Published: (2026)

Bluish Veil Detection and Lesion Classification using Custom Deep Learnable Layers with Explainable Artificial Intelligence (XAI)
by: Rasel, M. A., et al.
Published: (2025)

Beyond the Veil of Similarity: Quantifying Semantic Continuity in Explainable AI
by: Huang, Qi, et al.
Published: (2024)

From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information
by: Jiao, Qirui, et al.
Published: (2024)

MLLMs-Augmented Visual-Language Representation Learning
by: Liu, Yanqing, et al.
Published: (2023)

To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
by: Luo, Jiayun, et al.
Published: (2025)

LLaVA-UHD v3: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs
by: Sun, Shichu, et al.
Published: (2025)