Picture for DiJia Su

DiJia Su

Training Large Language Models to Reason in a Continuous Latent Space

Add code
Dec 09, 2024
Viaarxiv icon

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces

Add code
Oct 13, 2024
Viaarxiv icon

Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting

Add code
Jun 10, 2022
Figure 1 for Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting
Figure 2 for Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting
Figure 3 for Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting
Figure 4 for Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting
Viaarxiv icon

MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning

Add code
Feb 23, 2021
Figure 1 for MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning
Figure 2 for MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning
Figure 3 for MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning
Figure 4 for MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning
Viaarxiv icon