6 papers
Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models
Yijie Qian, Juncheng Wang, Chao Xu +6
As audio-visual generative models evolve into world simulators, cross-modal synchronization stands as a critical proxy for assessing the consistency of world dynamics and causality…
Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies
Yuxiang Feng, Juncheng Wang, Chao Xu +7
Forecasting the future anatomy of slow-evolving neurodegenerative diseases could enable earlier, more targeted intervention and improve clinical trial design, but it remains challe…
NEWTON: Agentic Planning for Physically Grounded Video Generation
Yuxiang Feng, Juncheng Wang, Chao Xu +7
Video generation models produce visually compelling results but systematically violate physical commonsense -- on VideoPhy-2, the best model achieves only 32.6% joint accuracy. We…
Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generation
Yijie Qian, Juncheng Wang, Yuxiang Feng +7
Current state-of-the-art paradigms predominantly treat Text-to-Motion (T2M) generation as a direct translation problem, mapping symbolic language directly to continuous poses. Whil…
Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving
Yu Yang, Jianbiao Mei, Yukai Ma +5
World models envision potential future states based on various ego actions. They embed extensive knowledge about the driving environment, facilitating safe and scalable autonomous…
Open-Vocabulary SAM3D: Towards Training-free Open-Vocabulary 3D Scene Understanding
Hanchen Tai, Qingdong He, Jiangning Zhang +6
Open-vocabulary 3D scene understanding presents a significant challenge in the field. Recent works have sought to transfer knowledge embedded in vision-language models from 2D to 3…