4 papers
Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning
Wenzheng Zeng, Siyi Jiao, Chen Gao +2
Dense video captioning aims to generate temporally grounded descriptions of video events, benefiting both event-level video understanding and generation. In this domain, autoregres…
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
Mingyu Ouyang, Siyuan Hu, Kevin Qinghong Lin +2
Towards an embodied generalist for real-world interaction, Multimodal Large Language Model (MLLM) agents still suffer from challenging latency, sparse feedback, and irreversible mi…
FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection
Mingyu Ouyang, Kevin Qinghong Lin, Mike Zheng Shou +1
Vision-Language Models (VLMs) have shown remarkable performance in User Interface (UI) grounding tasks, driven by their ability to process increasingly high-resolution screenshots.…
Factorized Learning for Temporally Grounded Video-Language Models
Wenzheng Zeng, Difei Gao, Mike Zheng Shou +1
Recent video-language models have shown great potential for video understanding, but still struggle with accurate temporal grounding for event-level perception. We observe that two…