Hanjun Dai

Faster WIND: Accelerating Iterative Best-of-N Distillation for LLM Alignment AISTATS 2025 Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF ICLR 2025 Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models ICML 2024 UQE: A Query Engine for Unstructured Databases NeurIPS 2024 Any-scale Balanced Samplers for Discrete Space ICLR 2023 Better Zero-Shot Reasoning with Self-Adaptive Prompting ACL 2023 Discrete Langevin Samplers via Wasserstein Gradient Flow AISTATS 2023 DISCS: A Benchmark for Discrete Sampling NeurIPS 2023 DocumentNet: Bridging the Data Gap in Document Pre-training EMNLP 2023 Gradient-Free Structured Pruning with Unlabeled Data ICML 2023 LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas NeurIPS 2023 Learning to Optimize with Stochastic Dominance Constraints AISTATS 2023 Learning Universal Policies via Text-Guided Video Generation NeurIPS 2023 Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets NeurIPS 2023 On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval EMNLP 2023 Revisiting Sampling for Combinatorial Optimization ICML 2023 Score-based Continuous-time Discrete Diffusion Models ICLR 2023 SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data EMNLP 2023 Universal Self-Adaptive Prompting EMNLP 2023 Video Timeline Modeling For News Story Understanding NeurIPS 2023 CodeTrek: Flexible Modeling of Code using an Extensible Relational Representation ICLR 2022 CrossBeam: Learning to Search in Bottom-Up Program Synthesis ICLR 2022 Does GNN Pretraining Help Molecular Representation? NeurIPS 2022 Marginal Distribution Adaptation for Discrete Sets via Module-Oriented Divergence Minimization ICML 2022 Neural Stochastic Dual Dynamic Programming ICLR 2022 Optimal Scaling for Locally Balanced Proposals in Discrete Spaces NeurIPS 2022 Path Auxiliary Proposal for MCMC in Discrete Space ICLR 2022 BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration ICLR 2021 Combiner: Full Attention Transformer with Sparse Computation Cost NeurIPS 2021 LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs ICML 2021 Molecule Optimization by Explainable Evolution ICLR 2021 SpreadsheetCoder: Formula Prediction from Semi-structured Context ICML 2021 Towards understanding retrosynthesis by energy-based models NeurIPS 2021 Differentiable Top-k with Optimal Transport NeurIPS 2020 Energy-Based Processes for Exchangeable Data ICML 2020 HOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DETECT AND FIX BUGS IN PROGRAMS ICLR 2020 Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration NeurIPS 2020 Learning To Stop While Learning To Predict ICML 2020 Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search ICML 2020 Scalable Deep Generative Modeling for Sparse Graphs ICML 2020 CompILE: Compositional Imitation Learning and Execution ICML 2019 Exponential Family Estimation via Adversarial Dynamics Embedding NeurIPS 2019 Kernel Exponential Family Estimation via Doubly Dual Embedding AISTATS 2019 Learning a Meta-Solver for Syntax-Guided Program Synthesis ICLR 2019 Learning Transferable Graph Exploration NeurIPS 2019 Particle Flow Bayes’ Rule ICML 2019 Retrosynthesis Prediction with Conditional Graph Logic Network NeurIPS 2019 Adversarial Attack on Graph Structured Data ICML 2018 Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification NeurIPS 2018 Coupled Variational Bayes via Optimization Embedding NeurIPS 2018 Learning Loop Invariants for Program Verification NeurIPS 2018 Learning Steady-States of Iterative Algorithms over Graphs ICML 2018 Syntax-Directed Variational Autoencoder for Structured Data ICLR 2018 Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs ICML 2017 Learning Combinatorial Optimization Algorithms over Graphs NeurIPS 2017 Discriminative Embeddings of Latent Variable Models for Structured Data ICML 2016 Provable Bayesian Inference via Particle Mirror Descent AISTATS 2016 M-Statistic for Kernel Change-Point Detection NeurIPS 2015 A Probabilistic Model for Learning Multi-Prototype Word Embeddings COLING 2014