Publications (85)
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
Chenyu Yang, Yuntao Chen, Hao Tian +9
We present a novel bird's-eye-view (BEV) detector with perspective supervision, which converges faster and better suits modern image backbones. Existing state-of-the-art BEV detect…
HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
Chenxin Tao, Shiqian Su, Xizhou Zhu +8
The rapid advance of Large Language Models (LLMs) has catalyzed the development of Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders, offer a p…
Omni-Perception Policy Optimization for Multimodal Emotion Reasoning
Zhiyuan Han, Beier Zhu, Wenwen Tong +6
We find that current emotion-oriented Omni-MLLMs still lack reliable omni-modal perception: they (i) underutilize multimodal cues in their reasoning trajectories and (ii) exhibit u…
OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
Kanzhi Cheng, Zehao Li, Zheng Ma +11
Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile tasks, with recent leading models achieving a marked performance leap…
Scaling Spatial Intelligence with Multimodal Foundation Models
Zhongang Cai, Ruisi Wang, Chenyang Gu +26
Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation m…
Learning to Prompt Segment Anything Models
Jiaxing Huang, Kai Jiang, Jingyi Zhang +4
Segment Anything Models (SAMs) like SEEM and SAM have demonstrated great potential in learning to segment anything. The core design of SAMs lies with Promptable Segmentation, which…