A video-language model that combines adaptive frame sampling, explicit timestamps, and a reinforcement-learning reward for refusing irrelevant queries, beating prior methods on QVHighlights by about 3.5%.
https://openai
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning
A video-language model that combines adaptive frame sampling, explicit timestamps, and a reinforcement-learning reward for refusing irrelevant queries, beating prior methods on QVHighlights by about 3.5%.