VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding
cs.CV, cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Qwen3-VL Technical Report
- MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism
- Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding
- Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
- Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
- GPT-4o System Card
- VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
- LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
- Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
- Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
- Memory-enhanced Retrieval Augmentation for Long Video Understanding
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