5 papers
I-Perceive: A Foundation Model for Vision-Language Active Perception
Yongxi Huang, Zhuohang Wang, Wenjing Tang +3
Active perception - the ability of a robot to proactively select viewpoints to acquire task-relevant information - is essential for robust operation in real-world environments. How…
Understanding Post-Training Structural Changes in Large Language Models
Xinyu He, Xianghui Cao
Post-training fundamentally alters the behavior of large language models (LLMs), yet its impact on the internal parameter space remains poorly understood. In this work, we conduct…
Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models
Wanli Peng, Xin Chen, Hang Fu +3
Recent advances in large language models (LLMs) have made a profound impact on our society and also raised new security concerns. Particularly, due to the remarkable inference abil…
Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs
Wenjing Tang, Xinyu He, Yongxi Huang +3
Task planning under uncertainty is essential for home-service robots operating in the real world. Tasks involve ambiguous human instructions, hidden or unknown object locations, an…
Knowledge NeRF: Few-shot Novel View Synthesis for Dynamic Articulated Objects
Wenxiao Cai, Xinyue Lei, Xinyu He +2
We present Knowledge NeRF to synthesize novel views for dynamic scenes. Reconstructing dynamic 3D scenes from few sparse views and rendering them from arbitrary perspectives is a c…