4 papers
EAGLE-360: Embodied Active Global-to-Local Exploration in 360
Jingtao Xu, Zizhuo Lin, Jianwen Sun +2
While Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in standard visual understanding, adapting them for active visual search in 360 pa…
Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models
Zizhuo Lin, Quanling Liu, Jinsheng Quan +6
Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gradually across turns. When a cl…
ParticleGS: Learning Neural Gaussian Particle Dynamics from Videos for Prior-free Physical Motion Extrapolation
Jinsheng Quan, Qiaowei Miao, Yichao Xu +5
The ability to extrapolate dynamic 3D scenes beyond the observed timeframe is fundamental to advancing physical world understanding and predictive modeling. Existing dynamic 3D rec…
Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
Chunshi Wang, Junliang Ye, Yunhan Yang +6
We introduce Part-X-MLLM, a native 3D multimodal large language model that unifies diverse 3D tasks by formulating them as programs in a structured, executable grammar. Given an RG…