On-Policy Visual Evidence Distillation
cs.CV, cs.AI, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- OPD-V: Visual On-Policy Self-Distillation with Modality Balance
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents
- Kimi K2.5: Visual Agentic Intelligence
- Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning
- Visual-Advantage On-Policy Distillation for Vision-Language Models
- V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Qwen3 Technical Report
- On-Policy Context Distillation for Language Models
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
- VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
- Group-Reflective Self-Distillation for Agentic Reinforcement Learning
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