EGSD: Event-Grounded Self-Distillation for Streaming Video Understanding

arXiv:2609.36803 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-10-05

Terminology

• Distillation — 18× in this paper · explained in 2 episodes
• Benchmark — 15× in this paper · explained in 2 episodes
• Grounding — 11× in this paper · explained in 3 episodes
• Self-distillation — 10× in this paper · explained in 6 episodes
• Computer Vision and Pattern Recognition — 5× in this paper
• Event-Grounded Self-Distillation — 5× in this paper
• On-Policy Distillation — 4× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Accuracy — 3× in this paper · explained in 1 episode
• Credit assignment — 3× in this paper · explained in 3 episodes
• GRPO — 2× in this paper · explained in 6 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 1× in this paper
• Cooperation — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
• PaLM-E: An Embodied Multimodal Language Model
• LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning
• MiniLLM: On-Policy Distillation of Large Language Models
• VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
• Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification
• video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
• MSJoE: Jointly Evolving MLLM and Sampler for Efficient Long-Form Video Understanding
• InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
• FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding
• Self-Distilled RLVR
• MiMo-VL Technical Report
• StepOPSD: Step-Aware Online Preference Self-Distillation for Agent Reinforcement Learning
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
• OPLD: On-Policy Latent Distillation for Multimodal 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