RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large Multi-modal Models.

VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning.

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?

FILP-3D: Enhancing 3D few-shot class-incremental learning with pre-trained vision-language models.

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition.

An Improved Baseline for Reasoning Segmentation with Large Language Model.