4 papers
LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning
Jiangyong Huang, Xiaojian Ma, Xiongkun Linghu +6
Developing vision-language models (VLMs) capable of understanding 3D scenes has been a longstanding research goal. Despite recent progress, 3D VLMs still struggle with spatial reas…
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding
Yue Fan, Xiaojian Ma, Rongpeng Su +4
This paper investigates the problem of understanding dynamic 3D scenes from egocentric observations, a key challenge in robotics and embodied AI. Unlike prior studies that explored…
LongViTU: Instruction Tuning for Long-Form Video Understanding
Rujie Wu, Xiaojian Ma, Hai Ci +5
This paper introduces LongViTU, a large-scale (~121k QA pairs, ~900h videos), automatically generated dataset for long-form video understanding. We propose a systematic approach th…
Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
Zhi Gao, Bofei Zhang, Pengxiang Li +7
The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to so…