activity
20242026
collaborators

11 papers

cs.CV2026

Towards Comprehensive Basketball Understanding

Yirong Hu, Jiayuan Rao, Yu Zhang +2

Understanding a basketball game requires recognizing events, localizing actions, identifying players, and relating these to structured game knowledge. Existing benchmarks primarily…

cs.AI2026

WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting

Zhaokai Wang, Tianlin Gui, Jiayuan Rao +3

Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available…

cs.CV2026

OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams

Yibin Yan, Jilan Xu, Shangzhe Di +2

Modern visual agents require representations that are general, causal, and physically structured to operate in real-time streaming environments. However, current vision foundation…

cs.CV2026

VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization

Yikun Liu, Yuan Liu, Shangzhe Di +8

Multimodal Large Language Models (MLLMs) have recently achieved remarkable success in visual-language understanding, demonstrating superior high-level semantic alignment within the…

cs.CV2026

Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning

Yudi Shi, Shangzhe Di, Qirui Chen +5

Video reasoning constitutes a comprehensive assessment of a model's capabilities, as it demands robust perceptual and interpretive skills, thereby serving as a means to explore the…

cs.CV2026

Revisiting Multi-Task Visual Representation Learning

Shangzhe Di, Zhonghua Zhai, Weidi Xie

Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised…