Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning Paper • 2510.24320 • Published Oct 28 • 18
Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents Paper • 2510.23691 • Published Oct 27 • 51
StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification Paper • 2411.07076 • Published Nov 11, 2024