13 papers
WebRider: Persona-Conditioned Intent Controllers for Live-Web Assistance
Zhi Li, Tao Zhou, Yeqing Li +2
Delegating a web task involves more than asking a question; it requires transferring a policy: what to verify, how to handle uncertainty, which preferences matter, and when to stop…
Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft
Zhou Ziheng, Huacong Tang, Jinyuan Zhang +9
Discovering causal regularities and applying them to build functional systems--the discovery-to-application loop--is a hallmark of general intelligence, yet evaluating this capacit…
Why Are We Moral? An LLM-based Agent Simulation Approach to Study Moral Evolution
Zhou Ziheng, Huacong Tang, Mingjie Bi +7
The evolution of morality presents a puzzle: natural selection should favor self-interest, yet humans developed moral systems promoting altruism. Traditional approaches must abstra…
MPM Lite: Linear Kernels and Integration without Particles
Xiang Feng, Yunuo Chen, Chang Yu +6
In this paper, we introduce MPM Lite, a new hybrid Lagrangian/Eulerian method that eliminates the need for particle-based quadrature at solve time. Standard MPM practices suffer fr…
Simple Role Assignment is Extraordinarily Effective for Safety Alignment
Zhou Ziheng, Jiakun Ding, Zhaowei Zhang +6
Principle-based alignment often lacks context sensitivity and completeness. Grounded in Theory of Mind, we propose role conditioning as a compact alternative: social roles (e.g., m…
AnimaMimic: Imitating 3D Animation from Video Priors
Tianyi Xie, Yunuo Chen, Yaowei Guo +5
Creating realistic 3D animation remains a time-consuming and expertise-dependent process, requiring manual rigging, keyframing, and fine-tuning of complex motions. Meanwhile, video…