Chi Harold Liu

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Computer Vision (2)Constitutional AI & AI Ethics (1)Red-Teaming & Adversarial Robustness (1)Tool Use & Agents (1)

Frequent co-authors

Lichao Wang (1)Zhaoxing Ren (1)Tianzhuo Yang (1)Jiaming Ji (1)

Papers (3)

Jun 1, 2026

Lichao Wang +6Jun 1, 2026·also Academy of Artificial Intelligence, PKU

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning

SafeMCP effectively mitigates the risks of power-seeking behaviors in LLM agents while maintaining their operational utility.

Lichao Wang, Zhaoxing Ren, Tianzhuo Yang +4

Constitutional AI & AI Ethics Red-Teaming & Adversarial Robustness Tool Use & Agents

Apr 29, 2026

Apr 29, 2026·also BIT, D_2022_CVPR) provides, HIT, University of Science and Technology +1

STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulation

Robots get a spatial-temporal reasoning boost with STARRY, a world model that aligns future predictions with action generation, leading to a significant jump in manipulation success.

Yuxuan Tian, Yurun Jin, Yukun Shi +2

Computer Vision Robotics & Embodied AI World Models & Planning

Mar 19, 2026

Rethinking MLLM Itself as a Segmenter with a Single Segmentation Token

Ditch the mask decoder: a single segmentation token can unlock competitive image segmentation directly from MLLMs.

Anqi Zhang, X. Ji, Xiaokang Ji +5

Architecture Design (Transformers, SSMs, MoE)Computer Vision Multimodal Models

Search

Chi Harold Liu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (3)