collaborators

6 papers

stat.ML2026

SPECTRA: State-Space Exogenous Context and Temporal-Frequency Resolution Architecture for Probabilistic Energy Forecasting

Hang Ye, Xinyan Jiang, Yuedong Shi +5

Modern power systems increasingly require probabilistic forecasts amid interacting uncertainties from renewable intermittency, flexible demand, market volatility, and weather-depen…

cs.AI2026

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability

Xinyan Jiang, Ninghao Liu, Di Wang +1

Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality th…

cs.LG2026

In-Context Learning Operates as Concept Subspace Learning

Wei Tang, Xinyan Jiang, Fakhri Karray +1

Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identify compact activation directi…

cs.CV2026

Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models

Chengsheng Zhang, Chenghao Sun, Xinyan Jiang +2

Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual-textual understanding, yet their reliability is critically undermined by hallucinations, i.e., the…

cs.LG2026

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency

Xinyan Jiang, Wenjing Yu, Di Wang +1

Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning. However, existing methods deriving vectors from stat…

cs.CL2025

HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models

Xinyan Jiang, Hang Ye, Yongxin Zhu +3

Large Language Models (LLMs) often generate hallucinations, producing outputs that are contextually inaccurate or factually incorrect. We introduce HICD, a novel method designed to…