8 papers
RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment
Qingchuan Ma, Yuexiao Ma, Xiang Meng +7
Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipating the effects of rotation, a…
One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding
Wang Chen, Yu Chen, Xiang Wang +3
Frame selection is essential for applying Large Multimodal Models (LMMs) to long videos due to severe frame redundancy and limited context windows. Since the appropriate frame budg…
WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation
Yuhui Zeng, Wang Chen, Jinfa Huang +5
Existing Large Vision-Language Models (LVLMs) struggle with long-form video understanding due to the quadratic computational cost of visual tokens. While recent efficient methods a…
Benchmarking Living-Screen-Native GUI Agents on Short-Video Platforms
Jiashu Yao, Heyan Huang, Daiqing Wu +5
GUI agents today assume a static screen, where the world is frozen between two actions. However, real interfaces such as short-video applications violate this assumption, as their…
Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
Wang Chen, Yuhui Zeng, Yongdong Luo +5
Frame selection is crucial due to high frame redundancy and limited context windows when applying Large Vision-Language Models (LVLMs) to long videos. Current methods typically sel…
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models
Tianyu Xie, Jinfa Huang, Yuexiao Ma +11
Evaluating omni-modal large language models (OLMs) in multi-party dialogue requires more than answer correctness on pre-segmented inputs. We introduce SocialOmni, an offline diagno…
Event-Anchored Frame Selection for Effective Long-Video Understanding
Wang Chen, Yongdong Luo, Yuhui Zeng +5
Massive frame redundancy and limited context window make efficient frame selection crucial for long-video understanding with large vision-language models (LVLMs). Prevailing approa…
Training-Free Multimodal Large Language Model Orchestration
Tianyu Xie, Yuexiao Ma, Yuhang Wu +5
Building interactive omni-modal assistants often relies on end-to-end multimodal alignment to fuse heterogeneous modalities, which incurs substantial data and compute costs and lim…