Reading-List

• Aug. XX, 2026 Periodic Topological Deep Learning for Polymer Design and Discovery, (Zeyu Wang)

• Aug. XX, 2026 Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge, (Yuxin Wu)

• Jul. XX, 2026 Forward-Free Diffusion Language Models, (Yicheng Tao)

• Jul. XX, 2026 Speculative Sampling For Faster Molecular Dynamics, (Yitian Wang)

• Jul. XX, 2026 Latent Thought Flow: Efficient Latent Reasoning in Large Language Models, (Haotian Liu)

• Jun. 15, 2026 What is the objective of reasoning with reinforcement learning? and Maximum Likelihood Reinforcement Learning, (Haotian Liu)

• Jun. 8, 2026 The Geometry of Noise: Why Diffusion Models Don’t Need Noise Conditioning, (Fanmeng Wang)

• Jun. 1, 2026 Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training and Modeling glycans with AlphaFold 3: capabilities, caveats, and limitations, (Zeyu Wang)

• May. 25, 2026 YuriiFormer: A Suite of Nesterov-Accelerated Transformers, (Minjie Cheng, Slides)

• May. 11, 2026 MACROGUIDE: Topological Guidance for Macrocycle Generation, (Yitian Wang)

• Apr. 20, 2026 LoRA and Privacy: When Random Projections Help (and When They Don’t), (Shen Yuan, Slides)

• Apr. 13, 2026 Generative Modeling of Molecular Dynamics Trajectories, (Minjie Cheng, Slides)

• Mar. 30, 2026 The path not taken: RLVR provably learns off the principals, (Yicheng Tao, Slides)

• Mar. 23, 2026 Training-Free Group Relative Policy Optimization, (Haotian Liu, Slides)

• Mar. 16, 2026 G-Merging: Graph Models Merging for Parameter-Efficient Multi-Task Knowledge Consolidation, (Yuxin Wu)

• Mar. 9, 2026 ZATOM-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials, (Angxiao Yue)

• Dec. 29, 2025 Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach and Hybrid Latent Reasoning via Reinforcement Learning, (Haotian Liu, Slides1 and Slides2)

• Dec. 22, 2025 RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance, (Haotian Liu, Slides)

• Dec. 15, 2025 Latent Collaboration in Multi-Agent Systems, (Yicheng Tao, Slides)

• Dec. 08, 2025 Muon Outperforms Adam in Tail-End Associative Memory Learning, (Angxiao Yue, Slides)

• Dec. 01, 2025 Uni-LoRA: One Vector is All You Need, (Yuxin Wu, Slides)

• Nov. 3, 2025 Unrolled Graph Neural Networks for Constrained Optimization and Graph Signal Generative Diffusion Models, (Minjie Cheng, Slides)

• Oct. 27, 2025 A Euclidean transformer for fast and stable machine learned force fields and MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models, (Yitian Wang)

• Oct. 20, 2025 Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics, (Fanmeng Wang, Slides)

• Oct. 13, 2025 APE-Bench I: Towards File-level Automated Proof Engineering of Formal Math Libraries, (Haotian Liu, Slides)

• Sep. 29, 2025 Learning Gaussian Mixture Models via Transformer Measure Flows, (Shen Yuan, Slides)

• Sep. 22, 2025 Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction, (Yicheng Tao, Slides)

• Sep. 18, 2025 Atom level enzyme active site scaffolding using RFdiffusion2, (Yitian Wang)

• Sep. 5, 2025 Uni-Mol3: A Multi-Molecular Foundation Model for Advancing Organic Reaction Modeling, (Fanmeng Wang, Slides)

• Aug. 29, 2025 Gaussian mixture layers for neural networks, (Shen Yuan, Slides)

• Jul. 4, 2025 A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce, (Yicheng Tao, Slides)

• Jun. 27, 2025 Quantum Doubly Stochastic Transformers, (Shen Yuan, Slides)

• Jun. 20, 2025 Self-improving diffusion models with synthetic data, (Haotian Liu, Slides)

• Jun. 13, 2025 Deep generative design of RNA family sequences, (Fanmeng Wang, Slides)

• May 26, 2025 Elucidating the Design Space of Multimodal Protein Language Models, (Angxiao Yue, Slides)

• Mar. 10, 2025 Graph contrastive learning of subcellular-resolution spatial transcriptomics improves cell type annotation and reveals critical molecular pathways, (Fengjiao Gong, Slides)

• Dec. 24, 2024 On Efficient Computation of Gromov-Wasserstein Distance, (Dunyao Xue, Junyi Lin, Slides)

• Dec. 17, 2024 ProteinWeaver: A Divide-and-Assembly Approach for Protein Backbone Design, (Yitian Wang, Slides)

• Dec. 10, 2024 GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training, (Haotian Liu, Slides)

• Dec. 3, 2024 Mixture of Parrots: Experts improve memorization more than reasoning, (Shen Yuan, Slides)

• Nov. 26, 2024 Full-Atom Peptide Design based on Multi-modal Flow Matching, (Minjie Cheng, Slides)

• Nov. 19, 2024 Your contrastive learning problem is secretly a distribution alignment problem, (Minjie Cheng, Slides)

• Nov. 12, 2024 HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning, (Haotian Liu, Slides)

• Oct. 22, 2024 SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models, (Yuxin Wu, Slides)

• Oct. 15, 2024 Generalized Protein Pocket Generation with Prior-Informed Flow Matching, (Fanmeng Wang, Slides)

• Oct. 8, 2024 Reconstructing growth and dynamic trajectories from single-cell transcriptomics data, (Fengjiao Gong, Slides)

• Sep. 24, 2024 SE(3) diffusion model with application to protein backbone generation, (Angxiao Yue, Slides)

• Jul. 18, 2024 Interpretable Rotation-Equivariant Quaternion Neural Networks for 3D Point Cloud Processing，（Angxiao Yue, Slides）

• Jul. 11, 2024 TextGrad: Automatic “Differentiation” via Text, (Shukai Gong, Slides)

• Jul. 4, 2024 QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation, (Shen Yuan, Slides)

• Jun. 13, 2024 Learning Hierarchical Protein Representations via Complete 3D Graph Networks, (Minjie Cheng, Slides)

• Jun. 06, 2024 Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformers, (Like Ma, Slides)

• May. 16, 2024 Kolmogorov–Arnold Networks, (Yuxin Wu, Slides)

• May. 9, 2024 Learning Latent Partial Matchings with Gumbel-IPF Networks, (Fengjiao Gong, Slides)

• Apr. 25, 2024 GTMGC: Using Graph Transformer to Predict Molecule’s Ground-State Conformation, (Fanmeng Wang, Slides)

• Mar. 21, 2024 ROLAND: Graph Learning Framework for Dynamic Graphs, (Ke Wan, Slides)

• Mar. 14, 2024 Teaching Large Language Models to Reason with Reinforcement Learning, (Angxiao Yue, Slides)

• Mar. 7, 2024 ResNet with one-neuron hidden layers is a Universal Approximator, (Shen Yuan, Slides)

• Feb. 29, 2024 Pre-training sequence, structure, and surface features for comprehensive protein representation learning, (Minjie Cheng, Slides)

• Jan. 18, 2024 LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODELS, (Yuxin Wu, Slides)

• Jan. 11, 2024 ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving, (Angxiao Yue, Slides)

• Dec. 28, 2023 Graph-MLP: Node Classification without Message Passing in Graph, (Ke Wan, Slides)

• Dec. 21, 2023 CoarsenConf: Equivariant Coarsening with Aggregated Attention for Molecular Conformer Generation, (Fanmeng Wang, Slides)

• Dec. 14, 2023 Transformer-VQ: Linear-Time Transformers via Vector Quantization, (Shen Yuan, Slides)

• Nov. 30, 2023 GraphGPT: Graph Instruction Tuning for Large Language Models, (Minjie Cheng, Slides)

• Nov. 9, 2023 Clifford group equivariant neural networks, (Angxiao Yue, Slides)

• Nov. 2, 2023 Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning, (Fengjiao Gong, Slides)

• Oct. 26, 2023 Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency, (Yuxin Wu, Slides)

• Oct. 12, 2023 MOREL: MULTI-OMICS RELATIONAL LEARNING, (Qingmei Wang, Slides)

• Oct. 5, 2023 Generative Agents: Interactive Simulacra of Human Behavior, (Shen Yuan, Slides)

• Sep. 22, 2023 Conditional Generative Modeling is All You Need for Marked Temporal Point Processes, (Ke Wan, Slides)

• Sep. 15, 2023 Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equation, (Minjie Cheng, Slides)

• Aug. 9, 2023 Structural Hawkes Processes for Learning Causal Structure from Discrete-Time Event Sequences, (Yuxin Wu, Slides)

• Jul. 26, 2023 3d Infomax Improves GNNs for Molecular Property Prediction, (Fanmeng Wang, Slides)

• Jul. 19, 2023 Efficiently Modeling Long Sequences with Structured State Spaces, (Shen Yuan, Slides)

• Jun. 21, 2023 Improving Generative Flow Networks with Path Regularization, (Fanmeng Wang, Slides)

• Jun. 14, 2023 Mega: Moving Average Equipped Gated Attention, (Yuxin Wu, Slides)

• Jun. 7, 2023 Training Neural Networks Without Gradients: A Scalable ADMM Approach, (Minjie Cheng, Slides)

• May 31, 2023 Clifford Neural Layers for PDE Modeling, (Angxiao Yue, Slides)

• May 24, 2023 Equivariant Diffusion for Molecule Generation in 3D, (Fanmeng Wang, Slides)

• Apr. 26, 2023 On the Equivalence of Decoupled Graph Convolution Network and Label Propagation, (Minjie Cheng, Slides)

• Apr. 19, 2023 Communication-Efficient Topologies for Decentralized Learning with O(1) Consensus Rate, (Fengjiao Gong, Slides)

• Mar. 16, 2023 The Monge Gap: A Regularizer to Learn All Transport Maps, (Shen Yuan, Slides)

• Mar. 9, 2023 Sinkhorn EM: an expectation-maximization algorithm based on entropic optimal transport, (Qingmei Wang)

• Mar. 2, 2023 Combining graph convolutional neural networks and label propagation, (Minjie Cheng, Slides)

• Feb. 23, 2023 Watch and Match Supercharging Imitation with Regularized Optimal Transport, (Yuxin Wu, Slides)

• Feb. 16, 2023 Federated Graph Representation Learning using Self-Supervision, (Fengjiao Gong, Slides)

• Dec. 29, 2022 Deep Equilibrium Approaches to Diffusion Models, (Fanmeng Wang, Slides)

• Dec. 15, 2022 Generalised Implicit Neural Representations, (Shen Yuan)

• Dec. 8, 2022 THPs: Topological Hawkes Processes for Learning Causal Structure on Event Sequences, (Qingmei Wang)

• Dec. 1, 2022 ON REPRESENTING LINEAR PROGRAMS BY GRAPH NEURAL NETWORKS, (Minjie Cheng, Slides)

• Nov. 24, 2022 Scaling Forward Gradient With Local Losses, (Fengjiao Gong, Slides)

• Nov. 17, 2022 GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation, (Fanmeng Wang, Slides)

• Nov. 10, 2022 Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions, (Minjie Cheng, Slides)

• Nov. 3, 2022 Annealed Training for Combinatorial Optimization on Graphs, (Shen Yuan, Slides)

• Oct. 27, 2022 Multi-Agent Adversarial Inverse Reinforcement Learning, (Yuxin Wu, Slides)

• Oct. 13, 2022 On the Gradient Formula for learning Generative Models with Regularized Optimal Transport Costs, (Yuzhou Nie, Slides)

• Sep. 29, 2022 Unsupervised Learning of Visual Features by Contrasting Cluster Assignments, (Qingmei Wang)

• Sep. 8, 2022 Understanding Collapse in Non-Contrastive Siamese Representation Learning, (Yajie Zhang, Slides)

• Sep. 1, 2022 Differentially Private Learning of Hawkes Processes, (Jiajia Sun, Slides)

• Aug. 25, 2022 Score-based generative modeling through stochastic differential equations, (Qingmei Wang)

• Aug. 18, 2022 Meta Optimal Transport, (Fengjiao Gong, Slides)

• Aug. 11, 2022 Wasserstein t-SNE, (Minjie Cheng, Slides)

• Jul. 21, 2022 Unsupervised ground metric learning using wasserstein eigenvectors, (Fanmeng Wang, Slides)

• Jun. 30, 2022 Amortized Projection Optimization for Sliced Wasserstein Generative Models, (Yue Xiang, Slides)

• Jun. 17, 2022 Deep Reinforcement Learning of Marked Temporal Point Processes, (Jiajia Sun, Slides)

• Jun. 9, 2022 Optimal Transport in Reproducing Kernel Hilbert Spaces: Theory and Applications, (Fengjiao Gong, Slides)

• Jun. 2, 2022 DECLARATIVE NETS THAT ARE EQUILIBRIUM MODELS, (Minjie Cheng)

• May 26, 2022 Recovering Stochastic Dynamics via Gaussian Schrödinger Bridges, (Yajie Zhang, Slides)

• May 12, 2022 E(n) Equivariant Normalizing Flows, (Fanmeng Wang, Slides)

• May 5, 2022 SE (3)-equivariant prediction of molecular wavefunctions and electronic densities and Equivariant message passing for the prediction of tensorial properties and molecular spectra, (Shen Yuan)

• Apr. 21, 2022 Top-N: Equivariant set and graph generation without exchangeability and Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds, (Minjie Cheng, Slides)

• Apr. 14, 2022 Continuous wasserstein-2 barycenter estimation without minimax optimization and Fast Discrete Distribution Clustering Using Wasserstein Barycenter with Sparse Support, (Fengjiao Gong, Slides)

• Apr. 7, 2022 Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes and Counterfactual Temporal Point Processes, (Qingmei Wang)

• Mar. 31, 2022 Comparing Three Notions of Discrete Ricci Curvature on Biological Networks, Wireless network capacity versus Ollivier-Ricci curvature under Heat-Diffusion (HD) protocol and Community detection on networks with Ricci flow, (Yue Xiang, Slides)

• Mar. 24, 2022 Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent, (Fanmeng Wang, Slides)

• Mar. 17, 2022 LieTransformer: Equivariant Self-Attention for Lie Groups and Sinkformers: Transformers with doubly stochastic attention, (Minjie Cheng, Slides)

• Mar. 10, 2022 Fast iterative solution of the optimal transport problem on graphs and Quadratically regularized optimal transport on graphs, (Fengjiao Gong, Slides)

• Mar. 3, 2022 Fast Estimation of Causal Interactions using Wold Processes and A Variational Inference Approach to Learning Multivariate Wold Processes, (Qingmei Wang, Slides)

• Dec. 30, 2021 Large-Margin Contrastive Learning with Distance Polarization Regularizer, (Minjie Cheng, Slides)

• Dec. 23, 2021 Equivariant Subgraph Aggregation Networks, (Shen Yuan, Slides)

• Dec. 16, 2021 Large-scale optimal transport map estimation using projection pursuit, (Yue Xiang, Slides)

• Dec. 9, 2021 A Regularized Wasserstein Framework for Graph Kernels, (Fengjiao Gong, Slides)

• Dec. 2, 2021 Multiple Instance Learning with Bag Dissimilarities and Bag similarity network for deep multi-instance learning, (Qingmei Wang, Slides)

• Nov. 25, 2021 Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks and Deep Set, (Minjie Cheng, Slides)

• Nov. 18, 2021 Decoupled Contrastive Learning and Debiased Contrastive Learning, (Shen Yuan, Slides)

• Nov. 11, 2021 Utility/Privacy Trade-off through the lens of Optimal Transport, (Fengjiao Gong, Slides)

• Nov. 4, 2021 Adversarial Graph Augmentation to Improve Graph Contrastive Learning and Prototypical Graph Contrastive Learning, (Qingmei Wang)

• Oct. 28, 2021 Generative models for graph-based protein design and Scaffold-based molecular design with a graph generative model, (Minjie Cheng, Slides)

• Oct. 21, 2021 Iterative Amortized Inference and Semi-amortized variational autoencoders, (Shen Yuan, Slides)

• Oct. 14, 2021 Reparameterizing the Birkhoff Polytope for Permutation Variational Inference and Learing Latent Permutations with Gumbel-Sinkhorn Networks, (Yue Xiang, Slides)

• Sep. 30, 2021 Run-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative Models, (Fengjiao Gong, Slides)

• Sep. 23, 2021 Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View, (Qingmei Wang, Slides)

• Sep. 17, 2021 Highly accurate protein structure prediction with AlphaFold, and Accurate prediction of protein structures and interactions using a three-track neural network, (Minjie Cheng, Slides)

• Sep. 10, 2021 A Particle-Evolving Method for Approximating the Optimal Transport Plan, (Yue Xiang, Slides)

• Sep. 3, 2021 Subgraph Augmentation with Application to Graph Mining, (Shen Yuan, Slides)

• Aug. 27, 2021 Deep Fourier Kernel for Self-Attentive Point Processes, (Qingmei Wang, Slides)

• Aug. 20, 2021 Drug Recommendation toward Safe Polypharmacy, (Minjie Cheng, Slides)

• Aug. 13, 2021 Towards domain-agnostic contrastive learning, (Fengjiao Gong, Slides)

• Aug. 6, 2021 RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning, (Shen Yuan, Slides)

• Jul. 30, 2021 GTA: Graph Truncated Attention for Retrosynthesis, (Yue Xiang, Slides)

• Jun. 25, 2021 Learning to make generalizable and diverse predictions for retrosynthesis, (Yue Xiang)

• Jun. 18, 2021 Molecular Transformer unifies reaction prediction and retrosynthesis across pharma chemical space, (Yue Xiang, Slides)

• Jun. 11, 2021 Retrosynthesis Prediction with Conditional Graph Logic Network, (Shen Yuan)

• Jun. 4, 2021 Retrosynthesis of multi-component metal−organic frameworks, (Shen Yuan)

• May 28, 2021 Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction, (Yue Xiang)

• May 21, 2021 Multiview Sensing With Unknown Permutations: An Optimal Transport Approach, (Shen Yuan, Slides)

• May 14, 2021 Computer-Assisted Retrosynthesis Based on Molecular Similarity, (Yue Xiang, Slides)

• May 7, 2021 A Graph to Graphs Framework for Retrosynthesis Prediction, (Shen Yuan)

• Apr. 30, 2021 Graphon Signal Processing, (Yue Xiang)

• Apr. 23, 2021 Optimal transport mapping via input convex neural networks, (Shen Yuan)

• Apr. 2, 2021 STRATEGIC NETWORK FORMATION WITH MANY AGENTS, (Shen Yuan)

• Mar. 26, 2021 The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation, (Yue Xiang, Slides)

• Mar. 19, 2021 Improved Complexity Bounds in the Wasserstein Barycenter Problem, (Zejun Xie, Slides)

• Mar. 12, 2021 The Multivariate Hawkes Process in High Dimensions: Beyond Mutual Excitation, (Shen Yuan, Slides)

• Mar. 5, 2021 Partial Gromov-Wasserstein Learning for Partial Graph Matching, (Yue Xiang, Slides)

• Feb. 26, 2021 Existence and consistency of Wasserstein barycenters, (Zejun Xie, Slides)

• Feb. 19, 2021 Fast and Flexible Temporal Point Processes with Triangular Maps, (Shen Yuan, Slides)

• Feb. 5, 2021 Online Sinkhorn: Optimal Transport distances from sample streams, (Yue Xiang, Slides)

• Jan. 29, 2021 Bayesian Inference for Optimal Transport with Stochastic Cost, (Zejun Xie, Slides)

• Jan. 22, 2021 Temporal Logic Point Processes, (Shen Yuan, Slides)

• Jan. 15, 2021 Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein, (Yue Xiang, Slides)