collaborators

8 papers

cs.AI2026

PATH: Next-Interval Prediction via Autoregressive Tree Hierarchy on Tabular Data

Pengxiang Cai, Wanchen Lian, Chenyang Liu +4

Interval prediction aims to achieve a target coverage level while producing intervals that are as short as possible. Many conformal regression pipelines first predict an uncertaint…

cs.AI2026

JustLLMGRPO: Radiographic Control for Chest X-Ray Generation

Pengxiang Cai, Xiaohan Li, Anglin Liu +3

Text-conditioned chest X-ray generation aims to synthesize realistic radiographs that faithfully depict specified findings. Existing work has primarily improved quality by updating…

cs.LG2026

Curriculum Reinforcement Learning Can Incentivize Reasoning Capacity in LLMs Beyond the Base Model

Pengxiang Cai, Tianchen Fang, Xiaohan Li +3

Reinforcement learning with verifiable rewards (RLVR) is widely viewed as a promising path toward continuously improving large language models. Recent works, however, suggest that…

cs.LG2026

Strengthening LLMs for Tabular Prediction with Structural Priors

Pengxiang Cai, Zihao Gao, Wanchen Lian +2

Tabular prediction has long been dominated by gradient-boosted decision trees and specialized deep tabular models, while large language models (LLMs) remain difficult to make compe…

cs.AI2026

Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?

Qingyuan Zeng, Ziyang Chen, Pengxiang Cai +5

Biomedical discovery often requires connecting broad biomedical knowledge with specific experimental or clinical data. Background knowledge suggests relevant mechanisms but is usua…

cs.LG2026

Don't Retrain, Just Reuse: Recovering Dual-Target Molecules from Single-Target Diffusion Models

Qingyuan Zeng, Pengxiang Cai, Zixin Guan +5

Designing a single molecule that modulates two targets is a promising strategy for polypharmacology, but it remains substantially harder than standard single-target generation beca…