7 papers
Cheng's Theorem in the Spectral Setting
Carolina Ruviaro
We prove a maximal diameter rigidity theorem for closed 3-dimensional Riemannian manifolds under a spectral lower bound for the Ricci curvature. We show that if , and…
Hidden Gauge Controls Feature Specialization in ReLU Networks
Tongxi Wang
The success of deep learning depends on learning useful representations, yet predicting how training organizes these representations across neurons remains difficult. In this work,…
Sharp Spectral Thresholds for Logit Fixed Points
Tongxi Wang
Softmax feedback systems are a common mathematical core of entropy-regularized reinforcement learning, logit game dynamics, population choice, and mean-field variational updates. T…
FBS: Modeling Native Parallel Reading inside a Transformer
Tongxi Wang
Large language models (LLMs) excel across many tasks, yet inference is still dominated by strictly token-by-token autoregression. Existing acceleration methods largely patch this p…
Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
Tongxi Wang, Zhuoyang Xia, Xinran Chen +1
Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stabl…
ChiEngMixBench: Evaluating Large Language Models on Expert-Style Chinese-English Terminology Mixing
Qingyan Yang, Tongxi Wang, Yunsheng Luo
Large language models increasingly mediate multilingual professional communication, where useful generation requires adapting to community conventions about which expressions are r…
Stability of In-Context Learning: A Spectral Coverage Perspective
Tongxi Wang, Zhuoyang Xia
In-context learning (ICL) is a pivotal capability for the practical deployment of large-scale language models, yet its reliability can vary substantially with the number of demonst…