Frame Differential On-Policy Self-Distillation for Video Reasoning
cs.CV
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/wannanfeng/video_reasoning
Terminology
Sources
- Qwen3-VL Technical Report
- VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Reinforcing Video Reasoning with Focused Thinking
- FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
- RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- LLaVA-OneVision: Easy Visual Task Transfer
- PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping
- VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
- VISD: Enhancing Video Reasoning via Structured Self-Distillation
- Understanding R1-Zero-Like Training: A Critical Perspective
- LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- Kimi K2: Open Agentic Intelligence
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning
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