Cover Image

Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shao, Zhenwei, Wang, Mingyang, Zhang, Weijun, Yu, Zhou, Pan, Wenwen, Yang, Yan, Wei, Tao, Zhang, Hongyuan, Yu, Jun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering
by: Yu, Zhou, et al.
Published: (2023)

Imp: Highly Capable Large Multimodal Models for Mobile Devices
by: Shao, Zhenwei, et al.
Published: (2024)

Mitigating Multilingual Hallucination in Large Vision-Language Models
by: Qu, Xiaoye, et al.
Published: (2024)

Making Large Vision Language Models to be Good Few-shot Learners
by: Liu, Fan, et al.
Published: (2024)

D2LLM: Decomposed and Distilled Large Language Models for Semantic Search
by: Liao, Zihan, et al.
Published: (2024)

MoPD: Mixture-of-Prompts Distillation for Vision-Language Models
by: Chen, Yang, et al.
Published: (2024)

A Survey of On-Policy Distillation for Large Language Models
by: Song, Mingyang, et al.
Published: (2026)

Dataset Distillation via Vision-Language Category Prototype
by: Zou, Yawen, et al.
Published: (2025)

GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning
by: Li, Yujun, et al.
Published: (2026)

Beyond the Vision Encoder: Identifying and Mitigating Spatial Bias in Large Vision-Language Models
by: Zhu, Yingjie, et al.
Published: (2025)

From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration
by: Song, Mingyang, et al.
Published: (2025)

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage
by: Wang, Yu, et al.
Published: (2024)

CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding
by: Zheng, Lihao, et al.
Published: (2026)

Unveiling the Tapestry of Consistency in Large Vision-Language Models
by: Zhang, Yuan, et al.
Published: (2024)

Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
by: Cao, Sihan, et al.
Published: (2026)

Enhance Vision-Language Alignment with Noise
by: Huang, Sida, et al.
Published: (2024)

DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding
by: Yu, Wenwen, et al.
Published: (2025)

Masking Teacher and Reinforcing Student for Distilling Vision-Language Models
by: Lee, Byung-Kwan, et al.
Published: (2025)

Explicit Multi-head Attention for Inter-head Interaction in Large Language Models
by: Peng, Runyu, et al.
Published: (2026)

Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models
by: Zhang, Tiezheng, et al.
Published: (2025)

Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game
by: Ye, Rong, et al.
Published: (2025)

UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
by: Zhou, Wenxuan, et al.
Published: (2023)

IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
by: Yang, Jiabing, et al.
Published: (2025)

Attacking Vision-Language Computer Agents via Pop-ups
by: Zhang, Yanzhe, et al.
Published: (2024)

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
by: Zhang, Ce, et al.
Published: (2025)

A Survey on Knowledge Distillation of Large Language Models
by: Xu, Xiaohan, et al.
Published: (2024)

Multi-Granularity Semantic Revision for Large Language Model Distillation
by: Liu, Xiaoyu, et al.
Published: (2024)

A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends
by: Liu, Daizong, et al.
Published: (2024)

Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning
by: Zhu, Yingjie, et al.
Published: (2024)

Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers
by: Ma, Ji, et al.
Published: (2025)

From Correction to Mastery: Reinforced Distillation of Large Language Model Agents
by: Lyu, Yuanjie, et al.
Published: (2025)

Accelerating Locality-Driven Integration in Quantum Chemistry with Block-Structured Matrix Multiplication
by: Wei, Xinran, et al.
Published: (2026)

Distilling Large Language Models for Text-Attributed Graph Learning
by: Pan, Bo, et al.
Published: (2024)

Vision-Language Dataset Distillation
by: Wu, Xindi, et al.
Published: (2023)

Conditional Pseudo-Supervised Contrast for Data-Free Knowledge Distillation
by: Shao, Renrong, et al.
Published: (2025)

Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate
by: Huang, Qidong, et al.
Published: (2024)

Direct Preference Knowledge Distillation for Large Language Models
by: Li, Yixing, et al.
Published: (2024)

TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge
by: Zhang, Shu-Hao, et al.
Published: (2025)

PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
by: Xing, Long, et al.
Published: (2024)

Compound Expression Recognition via Large Vision-Language Models
by: Yu, Jun, et al.
Published: (2025)