Image de couverture de livre

MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Kaichen, Huo, Jiahao, Yan, Yibo, Wang, Kun, Yue, Yutao, Hu, Xuming
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model
par: Huo, Jiahao, et autres
Publié: (2024)

Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey
par: Dang, Yunkai, et autres
Publié: (2024)

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models
par: Huo, Jiahao, et autres
Publié: (2025)

MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection
par: Yan, Yibo, et autres
Publié: (2025)

Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
par: Yan, Yibo, et autres
Publié: (2025)

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis
par: Huang, Haoming, et autres
Publié: (2025)

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models
par: Su, Jiamin, et autres
Publié: (2025)

Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models
par: Zheng, Kening, et autres
Publié: (2024)

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges
par: Yan, Yibo, et autres
Publié: (2024)

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection
par: Yan, Yibo, et autres
Publié: (2024)

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
par: Zhou, Guanyu, et autres
Publié: (2024)

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
par: Liu, Zheyuan, et autres
Publié: (2025)

GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning
par: Zhang, Jianghangfan, et autres
Publié: (2025)

On Relation-Specific Neurons in Large Language Models
par: Liu, Yihong, et autres
Publié: (2025)

Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models
par: Tang, Tianyi, et autres
Publié: (2024)

PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
par: Huo, Jiahao, et autres
Publié: (2025)

Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities
par: Zhang, Junyan, et autres
Publié: (2025)

MiningGPT -- A Domain-Specific Large Language Model for the Mining Industry
par: Demartini, Kurukulasooriya Fernando ana Gianluca
Publié: (2024)

Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations
par: Yan, Yibo, et autres
Publié: (2026)

CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding
par: Huo, Jiahao, et autres
Publié: (2026)

Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
par: Yan, Yibo, et autres
Publié: (2026)

Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
par: Yan, Yibo, et autres
Publié: (2026)

Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation
par: Zheng, Kening, et autres
Publié: (2026)

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
par: Huo, Jiahao, et autres
Publié: (2026)

EffiReason-Bench: A Unified Benchmark for Evaluating and Advancing Efficient Reasoning in Large Language Models
par: Huang, Junquan, et autres
Publié: (2025)

CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring
par: Su, Jiamin, et autres
Publié: (2025)

Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models
par: Siam, M. K. Khalidi, et autres
Publié: (2026)

Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining
par: Liu, Chenxi, et autres
Publié: (2025)

Aligning Translation-Specific Understanding to General Understanding in Large Language Models
par: Huang, Yichong, et autres
Publié: (2024)

ML-Mamba: Efficient Multi-Modal Large Language Model Utilizing Mamba-2
par: Huang, Wenjun, et autres
Publié: (2024)

Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval
par: Yan, Yibo, et autres
Publié: (2026)

CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models
par: Le, Yifan, et autres
Publié: (2026)

Evaluating and Steering Modality Preferences in Multimodal Large Language Model
par: Zhang, Yu, et autres
Publié: (2025)

Traj-MLLM: Can Multimodal Large Language Models Reform Trajectory Data Mining?
par: Liu, Shuo, et autres
Publié: (2025)

Reasoning Factual Knowledge in Structured Data with Large Language Models
par: Huang, Sirui, et autres
Publié: (2024)

SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification
par: Wang, Hongbo, et autres
Publié: (2025)

MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models
par: Wang, Xiaolong, et autres
Publié: (2025)

SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models
par: Cheng, Xianfu, et autres
Publié: (2025)

A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models
par: Liu, Shuliang, et autres
Publié: (2025)

Towards Reliable and Interpretable Traffic Crash Pattern Prediction and Safety Interventions Using Customized Large Language Models
par: Zhao, Yang, et autres
Publié: (2025)