EvoVid proposes a temporal-centric self-evolution framework for Video-LLMs that uses temporal-aware Questioner and temporal-grounded Solver rewards to improve performance directly from unannotated videos.
Vision-zero: Scalable vlm self-improvement via strategic gamified self-play
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3years
2026 3roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
EvoVid proposes a temporal-centric self-evolution framework for Video-LLMs that uses temporal-aware Questioner and temporal-grounded Solver rewards to improve performance directly from unannotated videos.
- RISE: Reliable Improvement in Self-Evolving Vision-Language Models
- Agentic AI for Remote Sensing: Technical Challenges and Research Directions