6 papers
Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering
Haotian Xia, Zilin Xiao, Junbo Zou +2
Video question answering requires models to ground language queries in visual evidence and, when necessary, reason over that evidence across time. Existing methods typically rely o…
VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding
Junbo Zou, Ziheng Huang, Shengjie Zhang +2
Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints and the need to capture informatio…
DeepSport: A Multimodal Large Language Model for Comprehensive Sports Video Reasoning via Agentic Reinforcement Learning
Junbo Zou, Haotian Xia, Zhen Ye +5
Sports video understanding requires perceiving high-speed dynamics, complex rules, and long temporal contexts. Yet, current Multimodal Large Language Models (MLLMs) remain narrowly…
SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports
Haotian Xia, Haonan Ge, Junbo Zou +16
Deeply understanding sports requires an intricate blend of fine-grained visual perception and rule-based reasoning - a challenge that pushes the limits of current multimodal models…
UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos
Zhi Yang, Lingfeng Zeng, Fangqi Lou +16
Multimodal large language models are playing an increasingly significant role in empowering the financial domain, however, the challenges they face, such as multimodal and high-den…
SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models
Haotian Xia, Zhengbang Yang, Junbo Zou +10
Multimodal Large Language Models (MLLMs) are advancing the ability to reason about complex sports scenarios by integrating textual and visual information. To comprehensively evalua…