Paper-Conference

Uniap: unifying inter-and intra-layer automatic parallelism by mixed integer quadratic programming

Tra-MoE: learning trajectory prediction model from multiple domains for adaptive policy conditioning

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

Taste more, taste better: diverse data and strong model boost semi-supervised crowd counting

Task preference optimization: improving multimodal large language models with vision task alignment

Steady progress beats stagnation: mutual aid of foundation and conventional models in mixed domain semi-supervised medical image segmentation

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning

Online video understanding: a comprehensive benchmark and memory-augmented method

Multiple object tracking as id prediction