1.1k citations · 4k across the 47 of their papers we have counts for
47 papers
On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval
Jiayi Chen, Hanjun Dai, Bo Dai +2
Visually-rich document entity retrieval (VDER), which extracts key information (e.g. date, address) from document images like invoices and receipts, has become an important topic i…
DocumentNet: Bridging the Data Gap in Document Pre-Training
Lijun Yu, Jin Miao, Xiaoyu Sun +4
Document understanding tasks, in particular, Visually-rich Document Entity Retrieval (VDER), have gained significant attention in recent years thanks to their broad applications in…
LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas
Kensen Shi, Hanjun Dai, Wen-Ding Li +2
Search is an important technique in program synthesis that allows for adaptive strategies such as focusing on particular search directions based on execution results. Several prior…
Better Zero-Shot Reasoning with Self-Adaptive Prompting
Xingchen Wan, Ruoxi Sun, Hanjun Dai +2
Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans. This is made possible…
Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets
Dinghuai Zhang, Hanjun Dai, Esmeralda S. Whitammer +3
Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning methods. The highly s…
Universal Self-Adaptive Prompting
Xingchen Wan, Ruoxi Sun, Hootan Nakhost +4
A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through in-context learning (ICL) via prompting. Howe…
Gradient-Free Structured Pruning with Unlabeled Data
Azade Nova, Hanjun Dai, Dale Schuurmans
Large Language Models (LLMs) have achieved great success in solving difficult tasks across many domains, but such success comes with a high computation cost, and inference latency.…
Learning Universal Policies via Text-Guided Video Generation
Yilun Du, Mengjiao Yang, Bo Dai +5
A goal of artificial intelligence is to construct an agent that can solve a wide variety of tasks. Recent progress in text-guided image synthesis has yielded models with an impress…
Score-based Continuous-time Discrete Diffusion Models
Haoran Sun, Lijun Yu, Bo Dai +2
Score-based modeling through stochastic differential equations (SDEs) has provided a new perspective on diffusion models, and demonstrated superior performance on continuous data.…
Learning to Optimize with Stochastic Dominance Constraints
Hanjun Dai, Yuan Xue, Niao He +4
In real-world decision-making, uncertainty is important yet difficult to handle. Stochastic dominance provides a theoretically sound approach for comparing uncertain quantities, bu…
Optimal Scaling for Locally Balanced Proposals in Discrete Spaces
Haoran Sun, Hanjun Dai, Dale Schuurmans
Optimal scaling has been well studied for Metropolis-Hastings (M-H) algorithms in continuous spaces, but a similar understanding has been lacking in discrete spaces. Recently, a fa…
Annealed Training for Combinatorial Optimization on Graphs
Haoran Sun, Etash K. Guha, Hanjun Dai
The hardness of combinatorial optimization (CO) problems hinders collecting solutions for supervised learning. However, learning neural networks for CO problems is notoriously diff…
Discrete Langevin Sampler via Wasserstein Gradient Flow
Haoran Sun, Hanjun Dai, Bo Dai +2
It is known that gradient-based MCMC samplers for continuous spaces, such as Langevin Monte Carlo (LMC), can be derived as particle versions of a gradient flow that minimizes KL di…
CrossBeam: Learning to Search in Bottom-Up Program Synthesis
Kensen Shi, Hanjun Dai, Kevin Ellis +1
Many approaches to program synthesis perform a search within an enormous space of programs to find one that satisfies a given specification. Prior works have used neural models to…
Exploring experimental conditions to reduce uncertainties in the optical potential
M. Catacora-Rios, G. B. King, A. E. Lovell +1
Background: Uncertainty quantification for nuclear theories has gained a more prominent role in the field, with more and more groups attempting to understand the uncertainties on t…
SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
Hongyu Ren, Hanjun Dai, Bo Dai +4
Knowledge graphs (KGs) capture knowledge in the form of head--relation--tail triples and are a crucial component in many AI systems. There are two important reasoning tasks on KGs:…
Combiner: Full Attention Transformer with Sparse Computation Cost
Hongyu Ren, Hanjun Dai, Zihang Dai +4
Transformers provide a class of expressive architectures that are extremely effective for sequence modeling. However, the key limitation of transformers is their quadratic memory a…
SpreadsheetCoder: Formula Prediction from Semi-structured Context
Xinyun Chen, Petros Maniatis, Rishabh Singh +4
Spreadsheet formula prediction has been an important program synthesis problem with many real-world applications. Previous works typically utilize input-output examples as the spec…
Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Hanjun Dai, Rishabh Singh, Bo Dai +2
Discrete structures play an important role in applications like program language modeling and software engineering. Current approaches to predicting complex structures typically co…
Polymers for Extreme Conditions Designed Using Syntax-Directed Variational Autoencoders
Rohit Batra, Hanjun Dai, Tran Doan Huan +5
The design/discovery of new materials is highly non-trivial owing to the near-infinite possibilities of material candidates, and multiple required property/performance objectives.…
BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration
Augustus Odena, Kensen Shi, David Bieber +3
Program synthesis is challenging largely because of the difficulty of search in a large space of programs. Human programmers routinely tackle the task of writing complex programs b…
Energy-based View of Retrosynthesis
Ruoxi Sun, Hanjun Dai, Li Li +2
Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery. Existing machine le…
Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search
Binghong Chen, Chengtao Li, Hanjun Dai +1
Retrosynthetic planning is a critical task in organic chemistry which identifies a series of reactions that can lead to the synthesis of a target product. The vast number of possib…
Scalable Deep Generative Modeling for Sparse Graphs
Hanjun Dai, Azade Nazi, Yujia Li +2
Learning graph generative models is a challenging task for deep learning and has wide applicability to a range of domains like chemistry, biology and social science. However curren…