activity
20242026
collaborators

8 papers

cs.LG2026

Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting

Xinyu Li, Yuanyuan Wang, Haoxuan Li +7

Causal discovery aims to uncover causal structures from observational data, which is crucial for real-world decision-making. However, different causal discovery algorithms can prod…

cs.MM2026

SRA: Semantic Relation-Aware Flowchart Question Answering

Xinyu Li, Bowei Zou, Yuchong Chen +2

Flowchart Question Answering (FlowchartQA) is a multi-modal task that automatically answers questions conditioned on graphic flowcharts. Current studies convert flowcharts into int…

cs.CL2025

ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models

Mingda Li, Xinyu Li, Weinan Zhang +1

Uncertainty Quantification (UQ) is a promising approach to improve model reliability, yet quantifying the uncertainty of Large Language Models (LLMs) is non-trivial. In this work,…

cs.LG2025

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Xinyu Li, Tianjin Huang, Ronghui Mu +2

Recent advances in Chain-of-Thought (CoT) prompting have substantially enhanced the reasoning capabilities of large language models (LLMs), enabling sophisticated problem-solving t…

cs.CL2025

Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models

Jiaming Li, Haoran Ye, Yukun Chen +5

Sparse Autoencoders (SAEs) are a cornerstone of mechanistic interpretability. Existing training methods inherit the Block Training paradigm from LLM pre-training, which introduces…

cs.LG2025

TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents

Yifu Cai, Xinyu Li, Mononito Goswami +3

We introduce TimeSeriesGym, a scalable benchmarking framework for evaluating Artificial Intelligence (AI) agents on time series machine learning engineering challenges. Existing be…