VideoEvoHarness: Self Evolving Agent Harness from Unlabeled Videos for Video Understanding
cs.CV
Submitted: 2026-10-11
Updated: 2026-10-11
Code: https://github.com/Wei-Xin-Xu/VideoEvoHarness
Terminology
Sources
- Qwen2.5-VL Technical Report
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
- MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding
- EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
- Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoning
- VisualClaw: A Real-Time, Personalized Agent for the Physical World
- Self-Harness: Harnesses That Improve Themselves
- Video-Zero: Self-Evolution Video Understanding
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
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