1 citations · 1 across the 10 of their papers we have counts for
13 papers
Minimal Witness Reinforcement Learning
T. Y. Tsui, Zihao Ye, Pengxiang Cai +3
``What are the irreducible conditions that are sufficient to produce an outcome?'' is one of the most common questions that recur across computation and science. Its answers, the m…
Robust Biomolecular Complex Design Across Protein Conformational Landscapes
Qingyuan Zeng, Zongqi Xu, Anglin Liu +7
Proteins populate conformational ensembles, yet structure-based biomolecular design typically optimizes candidates against a single target conformation. Consequently, a candidate t…
BIRD: Distilling Decision Boundaries into Rationales for MLLM Adaptation
Anglin Liu, Yanlin Wu, Ruichao Chen +6
Adapting general-purpose multimodal large language models (MLLMs) to specialized domains requires learning domain-specific decision criteria, which often hinge on subtle visual dis…
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…
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…
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…
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…
Don't Retrain, Just Reuse: Recovering Dual-Target Molecules from Single-Target Diffusion Models
Qingyuan Zeng, Pengxiang Cai, Zixin Guan +4
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…
MS-CustomNet: Controllable Multi-Subject Customization with Hierarchical Relational Semantics
Pengxiang Cai, Mengyang Li
Diffusion-based text-to-image generation has advanced significantly, yet customizing scenes with multiple distinct subjects while maintaining fine-grained control over their intera…
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…
ChemBOMAS: Accelerated BO in Chemistry with LLM-Enhanced Multi-Agent System
Dong Han, Zhehong Ai, Pengxiang Cai +16
Bayesian optimization (BO) is a powerful tool for scientific discovery in chemistry, yet its efficiency is often hampered by the sparse experimental data and vast search space. Her…
Auto DragGAN: Editing the Generative Image Manifold in an Autoregressive Manner
Pengxiang Cai, Zhiwei Liu, Guibo Zhu +2
Pixel-level fine-grained image editing remains an open challenge. Previous works fail to achieve an ideal trade-off between control granularity and inference speed. They either fai…
PFDM: Parser-Free Virtual Try-on via Diffusion Model
Yunfang Niu, Dong Yi, Lingxiang Wu +3
Virtual try-on can significantly improve the garment shopping experiences in both online and in-store scenarios, attracting broad interest in computer vision. However, to achieve h…