Shuiwang Ji

Professor@Texas A&M University·美国·OpenReview

研究方向

Physics simulation · AI for Science · Protein modeling · Drug discovery · Fluid flow simulations · Quantum mechanics · Density functional theory · Materials discovery · Equivariant graph networks

Shuiwang Ji

Orbital Transformers for Predicting Wavefunctions in Time-Dependent Density Functional Theory

A Joint Diffusion Model with Pre-Trained Priors for RNA Sequence-Structure Co-Design

Improving LLM Symbolic Problem-Solving via Automated Heuristic Discovery

Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning

Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design

A Two-Phase Deep Learning Framework for Adaptive Time-Stepping in High-Speed Flow Modeling

Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local Frames

Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training

Dynamic Search for Inference-Time Alignment in Diffusion Models

Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists

Learning Materials Interatomic Potentials via Hybrid Invariant-Equivariant Architectures

On Explaining Equivariant Graph Networks via Improved Relevance Propagation

Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-based Decoding

Learning to Discover Regulatory Elements for Gene Expression Prediction

Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design

Tensor Decomposition Networks for Accelerating Machine Learning Force Field Computations

Learning Time-Dependent Density Functional Theory via Geometry and Physics Aware Latent Evolution

Eliminating Position Bias of Language Models: A Mechanistic Approach

DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra

Geometry Informed Tokenization of Molecules for Language Model Generation

Geometry Informed Tokenization of Molecules for Language Model Generation

Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models

Discovering Physics Laws of Dynamical Systems via Invariant Function Learning

Discovering Physics Laws of Dynamical Systems via Invariant Function Learning

A Hierarchical Language Model Design For Interpretable Graph Reasoning

On Explaining Equivariant Graph Networks via Improved Relevance Propagation

Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding