Distill the Visual Evidence, Not Just the Answer: Cross-World On-Policy Distillation for Vision-Language Models
cs.CV
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/baokou-fw2/CWAD
Terminology
Sources
- SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
- Visual-Advantage On-Policy Distillation for Vision-Language Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models
- Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
- From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
- Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models
- Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models