Cover Image

Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Xin, Xi, Zhiheng, Ding, Yiwen, Zhai, Yitao, Shi, Xiaowei, Cai, Xunliang, Gui, Tao, Zhang, Qi, Huang, Xuanjing
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
by: Ding, Yiwen, et al.
Published: (2024)

Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models
by: He, Wei, et al.
Published: (2024)

Distill Visual Chart Reasoning Ability from LLMs to MLLMs
by: He, Wei, et al.
Published: (2024)

RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions
by: Zhang, Yuansen, et al.
Published: (2024)

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
by: Xi, Zhiheng, et al.
Published: (2023)

Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals
by: Zheng, Rui, et al.
Published: (2024)

LongHeads: Multi-Head Attention is Secretly a Long Context Processor
by: Lu, Yi, et al.
Published: (2024)

Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
by: Ye, Junjie, et al.
Published: (2025)

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
by: Xi, Zhiheng, et al.
Published: (2024)

LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
by: Zhao, Jun, et al.
Published: (2024)

Can RL Improve Generalization of LLM Agents? An Empirical Study
by: Xi, Zhiheng, et al.
Published: (2026)

Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data
by: Xia, Han, et al.
Published: (2024)

Contextual Experience Replay for Self-Improvement of Language Agents
by: Liu, Yitao, et al.
Published: (2025)

Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence
by: He, Jinghan, et al.
Published: (2024)

Unveiling Linguistic Regions in Large Language Models
by: Zhang, Zhihao, et al.
Published: (2024)

Improving RL Exploration for LLM Reasoning through Retrospective Replay
by: Dou, Shihan, et al.
Published: (2025)

Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMs
by: Ding, Zhikai, et al.
Published: (2025)

Improving Alignment in LVLMs with Debiased Self-Judgment
by: Yang, Sihan, et al.
Published: (2025)

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations
by: Li, Shuo, et al.
Published: (2025)

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
by: Lu, Yi, et al.
Published: (2025)

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
by: Xi, Zhiheng, et al.
Published: (2024)

MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning
by: Lin, Jiahang, et al.
Published: (2026)

Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models
by: Zhou, Xin, et al.
Published: (2025)

Better Process Supervision with Bi-directional Rewarding Signals
by: Chen, Wenxiang, et al.
Published: (2025)

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
by: Jin, Senjie, et al.
Published: (2025)

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
by: Li, Shuo, et al.
Published: (2024)

TailCue: Exploring Animal-inspired Robotic Tail for Automated Vehicles Interaction
by: Li, Yuan, et al.
Published: (2025)

Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
by: Wu, Yuanchen, et al.
Published: (2025)

MoTE: Mixture of Ternary Experts for Memory-efficient Large Multimodal Models
by: Wang, Hongyu, et al.
Published: (2025)

Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis
by: Wang, Siyin, et al.
Published: (2024)

Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training
by: Zhong, Qihuang, et al.
Published: (2026)

UniPaint: Unified Space-time Video Inpainting via Mixture-of-Experts
by: Wan, Zhen, et al.
Published: (2024)

ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing
by: Li, Shuo, et al.
Published: (2026)

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
by: Ye, Junjie, et al.
Published: (2024)

Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning
by: Xi, Zhiheng, et al.
Published: (2025)

Anti-Matthew FL: Bridging the Performance Gap in Federated Learning to Counteract the Matthew Effect
by: Gao, Jiashi, et al.
Published: (2023)

LLaMA Beyond English: An Empirical Study on Language Capability Transfer
by: Zhao, Jun, et al.
Published: (2024)

CCTU: A Benchmark for Tool Use under Complex Constraints
by: Ye, Junjie, et al.
Published: (2026)

Self-Distillation as a Performance Recovery Mechanism for LLMs: Counteracting Compression and Catastrophic Forgetting
by: Liu, Chi, et al.
Published: (2026)

Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection
by: de Senneville, Adhemar, et al.
Published: (2026)