activity
20242026
collaborators

10 papers

cs.LG2026

When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters

Fangxin Wang, Ziyi Zhang, Diyi Zhuang +4

Frozen pretrained forecasters often fail in structured, recurring ways that are costly to repair through fine-tuning. We study corrective feature discovery: mining interpretable fe…

cs.LG2026

Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning

Fangxin Wang, Peyman Baghershahi, Langzhou He +3

Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but existing methods are mostly designed for of…

cs.LG2026

GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs

Peyman Baghershahi, Fangxin Wang, Debmalya Mandal +1

Conformal prediction (CP) provides a distribution-free approach to uncertainty quantification with finite-sample guarantees. However, applying CP to graph neural networks (GNNs) re…

cs.CL2026

When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation

Henry Peng Zou, Chunyu Miao, Wei-Chieh Huang +16

As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as addi…

stat.ML2025

Topology-Aware Conformal Prediction for Stream Networks

Jifan Zhang, Fangxin Wang, Zihe Song +3

Stream networks, a unique class of spatiotemporal graphs, exhibit complex directional flow constraints and evolving dependencies, making uncertainty quantification a critical yet c…

cs.CL2025

RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback

Chunyu Miao, Henry Peng Zou, Yangning Li +28

Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing…