6 papers
TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories
Daniel Agyei Asante, Yang Li
Long-context compression is essential for reducing the cost and latency of large language model inference. However, existing methods can fragment important evidence, require additi…
DReSG: Diffusion Residuals for Stylized Gaussian Splatting
Zhongliang Liu, Wenjie Liu, Yang Li
Reference-guided stylization of scenes represented by 3D Gaussian Splatting (3DGS) is important for efficient and controllable 3D content creation. Existing VGG-feature-based 3D st…
Parameter Estimation of Power Electronic Converters with Differentiable Physics Simulation
Pingjunjin Tan, Chunlin Lv, Jinjun Liu +1
This article proposes a differentiable physics simulation (DP simulation)-based parameter estimation method for the condition monitoring of power electronic converters. In the prop…
The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal
Md Mokarram Chowdhury, Ernie Chang, Yang Li
Large language models are trained to follow instructions while refusing harmful requests. Jailbreaks exploit this balance to elicit content a model would ordinarily reject. Rolepla…
Refined decay estimates for global solutions to the rotating MHD equations
Mikihiro Fujii, Yang Li
In this paper, we consider the Cauchy problem for the incompressible magnetohydrodynamic equations with the Coriolis force in the three-dimensional whole space. For large initial d…
Agentic AI uncovers conserved cross-tissue protein co-abundance programs inaccessible to single-dataset analysis
Runyu Guan, Dehao Wu, Qiqi Xie +2
Protein co-abundance clusters preserved across tissues can reveal shared disease mechanisms and candidate therapeutic targets, particularly when proteins implicated in organ-confin…