Teach with Blinks: Breaking Linguistic Momentum in On-Policy Distillation for Fine-Grained Multimodal Perception
cs.CV
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/Supltz/BlinkOPD
Terminology
Sources
- OPD-V: Visual On-Policy Self-Distillation with Modality Balance
- Qwen3-VL Technical Report
- GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- Evidence-Aligned Multimodal On-Policy Self-Distillation for Fine-Grained Visual Understanding
- Visual Contrastive Self-Distillation
- OPD-Aha: From Linguistic Momentum to Visual Reflection in Multimodal On-Policy Distillation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- V-Zero: Gating On-Policy Distillation with Contrastive Visual Evidence for Fine-Grained Visual Reasoning
- CV-OPD: Contrastive Vision On-policy Distillation
- VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
- RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models
- When Teacher Guidance Misleads: Reward-Aligned On-Policy Distillation
- On the Off-Policy Teacher in On-Policy Distillation
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs