5 papers
On-Policy Self-Distillation in Diffusion Models
Wei Zhou, Xiongwei Zhu, Lingdong Kong +14
Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction…
Model Effect or Label Effect? Refined Annotations and a Human-Referenced Benchmark for Pulmonary Embolism Segmentation
Qihang Sun, Zhongxiao Liu, Bailiang Jian +6
Purpose: To quantify how evaluation annotations influence measured pulmonary embolism (PE) segmentation performance relative to model training changes, and to establish a human-ref…
A High-Accuracy Numerical Homogenization Framework for Quasiperiodic Hamilton--Jacobi Equations
Kai Jiang, Meng Li, Juan Zhang +1
In this work, we develop an accurate numerical homogenization framework for computing effective Hamiltonians of quasiperiodic Hamilton--Jacobi equations (QHJEs) with convex Hamilto…
Scattering-Induced Magnon Layer-Hall Transport beyond Band Geometry
Zhiping Xue, Zhoujian Sun, Xiyin Ye +2
The layer Hall effect has been exclusively attributed to layer-locked Berry curvature, posing a fundamental barrier to its realization in conventional magnets. Here we report a fun…
From Causal Plausibility to Causal Reliability: Evaluating LLMs as Calibrated Direct Causal-Edge Classifiers
Amit Kumar, Elnur Adl Zarabi, Suranjana Trivedy +4
Large language models (LLMs) are increasingly used to provide prior causal knowledge for structural causal discovery, yet whether their direct-edge judgments and confidence can be…