Paper-Conference

Balanced direction from multifarious choices: arithmetic meta-learning for domain generalization

AutoLUT: LUT-based image super-resolution with automatic sampling and adaptive residual learning

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning

MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models

CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding