Picture for Honglak Lee

Honglak Lee

University of Michigan, Ann Arbor

A self-supervised framework for learning whole slide representations

Add code
Feb 09, 2024
Viaarxiv icon

TOD-Flow: Modeling the Structure of Task-Oriented Dialogues

Add code
Dec 07, 2023
Figure 1 for TOD-Flow: Modeling the Structure of Task-Oriented Dialogues
Figure 2 for TOD-Flow: Modeling the Structure of Task-Oriented Dialogues
Figure 3 for TOD-Flow: Modeling the Structure of Task-Oriented Dialogues
Figure 4 for TOD-Flow: Modeling the Structure of Task-Oriented Dialogues
Viaarxiv icon

Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models

Add code
Dec 05, 2023
Viaarxiv icon

Code Models are Zero-shot Precondition Reasoners

Add code
Nov 16, 2023
Figure 1 for Code Models are Zero-shot Precondition Reasoners
Figure 2 for Code Models are Zero-shot Precondition Reasoners
Figure 3 for Code Models are Zero-shot Precondition Reasoners
Figure 4 for Code Models are Zero-shot Precondition Reasoners
Viaarxiv icon

MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning

Add code
Oct 25, 2023
Figure 1 for MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning
Figure 2 for MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning
Figure 3 for MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning
Figure 4 for MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning
Viaarxiv icon

Combining Behaviors with the Successor Features Keyboard

Add code
Oct 24, 2023
Viaarxiv icon

From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning

Add code
Oct 24, 2023
Viaarxiv icon

Merging Generated and Retrieved Knowledge for Open-Domain QA

Add code
Oct 22, 2023
Figure 1 for Merging Generated and Retrieved Knowledge for Open-Domain QA
Figure 2 for Merging Generated and Retrieved Knowledge for Open-Domain QA
Figure 3 for Merging Generated and Retrieved Knowledge for Open-Domain QA
Figure 4 for Merging Generated and Retrieved Knowledge for Open-Domain QA
Viaarxiv icon

CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation

Add code
Oct 19, 2023
Viaarxiv icon

Guide Your Agent with Adaptive Multimodal Rewards

Add code
Sep 19, 2023
Viaarxiv icon