Picture for Hanjun Dai

Hanjun Dai

Combiner: Full Attention Transformer with Sparse Computation Cost

Add code
Jul 12, 2021
Figure 1 for Combiner: Full Attention Transformer with Sparse Computation Cost
Figure 2 for Combiner: Full Attention Transformer with Sparse Computation Cost
Figure 3 for Combiner: Full Attention Transformer with Sparse Computation Cost
Figure 4 for Combiner: Full Attention Transformer with Sparse Computation Cost
Viaarxiv icon

SpreadsheetCoder: Formula Prediction from Semi-structured Context

Add code
Jun 26, 2021
Figure 1 for SpreadsheetCoder: Formula Prediction from Semi-structured Context
Figure 2 for SpreadsheetCoder: Formula Prediction from Semi-structured Context
Figure 3 for SpreadsheetCoder: Formula Prediction from Semi-structured Context
Figure 4 for SpreadsheetCoder: Formula Prediction from Semi-structured Context
Viaarxiv icon

Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration

Add code
Nov 10, 2020
Figure 1 for Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Figure 2 for Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Figure 3 for Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Figure 4 for Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Viaarxiv icon

Polymers for Extreme Conditions Designed Using Syntax-Directed Variational Autoencoders

Add code
Nov 04, 2020
Figure 1 for Polymers for Extreme Conditions Designed Using Syntax-Directed Variational Autoencoders
Figure 2 for Polymers for Extreme Conditions Designed Using Syntax-Directed Variational Autoencoders
Figure 3 for Polymers for Extreme Conditions Designed Using Syntax-Directed Variational Autoencoders
Figure 4 for Polymers for Extreme Conditions Designed Using Syntax-Directed Variational Autoencoders
Viaarxiv icon

Energy-based View of Retrosynthesis

Add code
Jul 14, 2020
Figure 1 for Energy-based View of Retrosynthesis
Figure 2 for Energy-based View of Retrosynthesis
Figure 3 for Energy-based View of Retrosynthesis
Figure 4 for Energy-based View of Retrosynthesis
Viaarxiv icon

Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search

Add code
Jun 29, 2020
Figure 1 for Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search
Figure 2 for Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search
Figure 3 for Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search
Figure 4 for Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search
Viaarxiv icon

Scalable Deep Generative Modeling for Sparse Graphs

Add code
Jun 28, 2020
Figure 1 for Scalable Deep Generative Modeling for Sparse Graphs
Figure 2 for Scalable Deep Generative Modeling for Sparse Graphs
Figure 3 for Scalable Deep Generative Modeling for Sparse Graphs
Figure 4 for Scalable Deep Generative Modeling for Sparse Graphs
Viaarxiv icon

Learning to Stop While Learning to Predict

Add code
Jun 09, 2020
Figure 1 for Learning to Stop While Learning to Predict
Figure 2 for Learning to Stop While Learning to Predict
Figure 3 for Learning to Stop While Learning to Predict
Figure 4 for Learning to Stop While Learning to Predict
Viaarxiv icon

Energy-Based Processes for Exchangeable Data

Add code
Mar 17, 2020
Figure 1 for Energy-Based Processes for Exchangeable Data
Figure 2 for Energy-Based Processes for Exchangeable Data
Figure 3 for Energy-Based Processes for Exchangeable Data
Figure 4 for Energy-Based Processes for Exchangeable Data
Viaarxiv icon

Differentiable Top-k Operator with Optimal Transport

Add code
Feb 18, 2020
Figure 1 for Differentiable Top-k Operator with Optimal Transport
Figure 2 for Differentiable Top-k Operator with Optimal Transport
Figure 3 for Differentiable Top-k Operator with Optimal Transport
Figure 4 for Differentiable Top-k Operator with Optimal Transport
Viaarxiv icon