Ya-Qin Zhang

X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

Vector Quantization using Gaussian Variational Autoencoder

Coder as Editor: Code‑driven Interpretable Molecular Optimization

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens

Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

PE-SGD: Differentially Private Deep Learning via Evolution of Gradient Subspace for Text

Feedforward 4D Reconstruction for Dynamic Driving Scenes using Unposed Images

Drugging the Undruggable: Benchmarking and Modeling Fragment-Based Screening

ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute

AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation

CIDD: Collaborative Intelligence for Structure-Based Drug Design Empowered by LLMs

Redefining the task of Bioactivity Prediction

Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior

Reframing Structure-Based Drug Design Model Evaluation via Metrics Correlated to Practical Needs

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion

Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solvers