TempR1 applies temporal-aware multi-task RL using GRPO and three types of localization rewards to achieve SOTA temporal understanding in MLLMs with synergistic gains from joint optimization.
Effi- cient temporal extrapolation of multimodal large language models with temporal grounding bridge
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning
TempR1 applies temporal-aware multi-task RL using GRPO and three types of localization rewards to achieve SOTA temporal understanding in MLLMs with synergistic gains from joint optimization.
- Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey