5 papers
Physics-guided diffusion models for inverse design of disordered metamaterials
Ziyuan Xie, Weipeng Xu, Dazhi Zhao +6
Disordered metamaterials are promising for programming physical properties across diverse applications, yet their inverse design remains challenging due to the non-intuitive struct…
Chronos: Learning Temporal Dynamics of Reasoning Chains for Test-Time Scaling
Kai Zhang, Jiayi Liao, Chengpeng Li +3
Test-Time Scaling (TTS) has emerged as an effective paradigm for improving the reasoning performance of large language models (LLMs). However, existing methods -- most notably majo…
Style-constrained inverse design of microstructures with tailored mechanical properties using unconditional diffusion models
Weipeng Xu, Ziyuan Xie, Haoju Lin +3
Deep generative models, particularly denoising diffusion models, have achieved remarkable success in high-fidelity generation of architected microstructures with desired properties…
SAFER: Probing Safety in Reward Models with Sparse Autoencoder
Wei Shi, Ziyuan Xie, Sihang Li +1
Reinforcement learning from human feedback (RLHF) is a key paradigm for aligning large language models (LLMs) with human values, yet the reward models at its core remain largely op…
Aerial Path Online Planning for Urban Scene Updation
Mingfeng Tang, Ningna Wang, Ziyuan Xie +4
We present the first scene-update aerial path planning algorithm specifically designed for detecting and updating change areas in urban environments. While existing methods for lar…