Image de couverture de livre

SDRT: Enhance Vision-Language Models by Self-Distillation with Diverse Reasoning Traces

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Guande, Song, Huan, Wang, Yawei, Yan, Qiaojing, Tian, Yijun, Cheong, Lin Lee, Xu, Panpan
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reinforcement Learning for Self-Improving Agent with Skill Library
par: Wang, Jiongxiao, et autres
Publié: (2025)

VISD: Enhancing Video Reasoning via Structured Self-Distillation
par: Lin, Hao, et autres
Publié: (2026)

Elucidating the Preconditioning in Consistency Distillation
par: Zheng, Kaiwen, et autres
Publié: (2025)

Vision Transformers with Self-Distilled Registers
par: Chen, Yinjie, et autres
Publié: (2025)

Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation
par: Zhu, Chunzheng, et autres
Publié: (2026)

Distillation Dynamics: Towards Understanding Feature-Based Distillation in Vision Transformers
par: Tian, Huiyuan, et autres
Publié: (2025)

Vision-Language Dataset Distillation
par: Wu, Xindi, et autres
Publié: (2023)

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
par: Wang, Chenfeng, et autres
Publié: (2026)

SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph
par: Li, Jiazheng, et autres
Publié: (2025)

Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models
par: Liu, Zhaoyi, et autres
Publié: (2025)

Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap
par: Xu, Yige, et autres
Publié: (2026)

Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models
par: Hu, Yushi, et autres
Publié: (2023)

Trajectory-Diversity-Driven Robust Vision-and-Language Navigation
par: Li, Jiangyang, et autres
Publié: (2026)

ViTCN: Vision Transformer Contrastive Network For Reasoning
par: Song, Bo, et autres
Publié: (2024)

Optimized View and Geometry Distillation from Multi-view Diffuser
par: Zhang, Youjia, et autres
Publié: (2023)

Enhancing Vision-Language Models Generalization via Diversity-Driven Novel Feature Synthesis
par: Yan, Siyuan, et autres
Publié: (2024)

Score Distillation of Flow Matching Models
par: Zhou, Mingyuan, et autres
Publié: (2025)

Diverse Score Distillation
par: Xu, Yanbo, et autres
Publié: (2024)

AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation
par: Guo, Wenxuan, et autres
Publié: (2026)

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step
par: Xu, Guowei, et autres
Publié: (2024)

AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models
par: Li, Yuqi, et autres
Publié: (2025)

RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics
par: Zhou, Enshen, et autres
Publié: (2025)

VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation
par: Bousselham, Walid, et autres
Publié: (2025)

PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation
par: Umam, Ardian, et autres
Publié: (2023)

Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models
par: Balazadeh, Vahid, et autres
Publié: (2024)

ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models
par: Ye, Wencheng, et autres
Publié: (2025)

Distilling Vision-Language Models on Millions of Videos
par: Zhao, Yue, et autres
Publié: (2024)

Self-Rewarding Vision-Language Model via Reasoning Decomposition
par: Li, Zongxia, et autres
Publié: (2025)

POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion
par: Liu, Yuan, et autres
Publié: (2025)

FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language Models
par: Pyo, Jiyoon, et autres
Publié: (2025)

Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization
par: Li, Jinlong, et autres
Publié: (2024)

Adversarial Prompt Distillation for Vision-Language Models
par: Luo, Lin, et autres
Publié: (2024)

VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism
par: Zhang, Congzhi, et autres
Publié: (2025)

MPCAR: Multi-Perspective Contextual Augmentation for Enhanced Visual Reasoning in Large Vision-Language Models
par: Rahman, Amirul, et autres
Publié: (2025)

Visual-Advantage On-Policy Distillation for Vision-Language Models
par: Liu, Ruiqi, et autres
Publié: (2026)

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
par: Yoon, Hee Suk, et autres
Publié: (2026)

From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers
par: Tian, Huiyuan, et autres
Publié: (2025)

1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation
par: Li, Haoyu, et autres
Publié: (2026)

Synthetic Vasculature and Pathology Enhance Vision-Language Model Reasoning
par: Li, Chenjun, et autres
Publié: (2025)

Distillation-Enhanced Physical Adversarial Attacks
par: Liu, Wei, et autres
Publié: (2025)