activity
20242026
collaborators

10 papers

cs.LG2026

Are LLMs Ready for Neural-integrated Mechanistic Modeling? A Benchmark and Agentic Framework

Zihan Guan, Rituparna Datta, Mengxuan Hu +5

Large language models (LLMs) have shown promise in constructing mechanistic models from data. However, existing evaluations largely focus on simplified settings and fail to capture…

cs.CV2026

Enhanced Diagnostic Performance via Large-Resolution Inference Optimization for Pathology Foundation Models

Mengxuan Hu, Zihan Guan, John Kang +2

Despite their prominent performance on tasks such as ROI classification and segmentation, many pathology foundation models remain constrained by a specific input size e.g. 224 x 22…

cs.LG2025

BEACON: Bayesian Optimal Stopping for Efficient LLM Sampling

Guangya Wan, Zixin Stephen Xu, Sasa Zorc +4

Sampling multiple responses is a common way to improve LLM output quality, but it comes at the cost of additional computation. The key challenge is deciding when to stop generating…

cs.AI2025

BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing

Dongliang Guo, Mengxuan Hu, Zihan Guan +2

Large multi-modal models inevitably decay over time as facts update and previously learned information becomes outdated. Traditional approaches such as fine-tuning are often imprac…

cs.LG2025

Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety

Zihan Guan, Mengxuan Hu, Ronghang Zhu +2

Recent studies have uncovered a troubling vulnerability in the fine-tuning stage of large language models (LLMs): even fine-tuning on entirely benign datasets can lead to a signifi…

cs.CL2025

Large Language Models for Causal Discovery: Current Landscape and Future Directions

Guangya Wan, Yunsheng Lu, Yuqi Wu +2

Causal discovery (CD) and Large Language Models (LLMs) have emerged as transformative fields in artificial intelligence that have evolved largely independently. While CD specialize…