Runze Xia — accepted AI-conference papers

2026

Sampling-Free Uncertainty Quantification via Hidden State Dynamics in Language Models

Yixin Bu, Guanyun Zou, Renzhi Wang, Runze Xia, Cunjun Wang, Hongliang Dai +2

AAAI 2026technical

Large language models (LLMs) demonstrate remarkable capabilities in various complex language tasks, yet they face significant reliability challenges, including factual inaccuracies and generated biases. Uncertainty quantification (UQ) plays a pivotal role in assessing model trustworthiness, particul

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Energy Landscape-Aware Vision Transformers: Layerwise Dynamics and Adaptive Task-Specific Training via Hopfield States

Runze Xia, Richard Jiang

NeurIPS 2025poster

Recent advances in Vision Transformers (ViTs) have shown remarkable performance across vision tasks, yet their deep, uniform layer structure introduces significant computational overhead. In this work, we explore the emergent dynamics of ViT layers through the lens of energy-based memory systems, dr…

Cited by 0 Source ↗Scholar ↗