Picture for Nevan Wichers

Nevan Wichers

Visualizing Neural Network Imagination

Add code
May 10, 2024
Viaarxiv icon

Gradient-Based Language Model Red Teaming

Add code
Jan 30, 2024
Viaarxiv icon

DRLC: Reinforcement Learning with Dense Rewards from LLM Critic

Add code
Jan 14, 2024
Viaarxiv icon

SiRA: Sparse Mixture of Low Rank Adaptation

Add code
Nov 15, 2023
Figure 1 for SiRA: Sparse Mixture of Low Rank Adaptation
Figure 2 for SiRA: Sparse Mixture of Low Rank Adaptation
Figure 3 for SiRA: Sparse Mixture of Low Rank Adaptation
Figure 4 for SiRA: Sparse Mixture of Low Rank Adaptation
Viaarxiv icon

Fusion-Eval: Integrating Evaluators with LLMs

Add code
Nov 15, 2023
Figure 1 for Fusion-Eval: Integrating Evaluators with LLMs
Figure 2 for Fusion-Eval: Integrating Evaluators with LLMs
Figure 3 for Fusion-Eval: Integrating Evaluators with LLMs
Figure 4 for Fusion-Eval: Integrating Evaluators with LLMs
Viaarxiv icon

SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition

Add code
Feb 10, 2022
Figure 1 for SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition
Figure 2 for SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition
Figure 3 for SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition
Figure 4 for SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition
Viaarxiv icon

ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces

Add code
Jan 25, 2021
Figure 1 for ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces
Figure 2 for ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces
Figure 3 for ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces
Figure 4 for ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces
Viaarxiv icon

RL agents Implicitly Learning Human Preferences

Add code
Feb 14, 2020
Figure 1 for RL agents Implicitly Learning Human Preferences
Figure 2 for RL agents Implicitly Learning Human Preferences
Viaarxiv icon

Resolving Spurious Correlations in Causal Models of Environments via Interventions

Add code
Feb 12, 2020
Viaarxiv icon

Resolving Referring Expressions in Images With Labeled Elements

Add code
Oct 25, 2018
Figure 1 for Resolving Referring Expressions in Images With Labeled Elements
Figure 2 for Resolving Referring Expressions in Images With Labeled Elements
Figure 3 for Resolving Referring Expressions in Images With Labeled Elements
Figure 4 for Resolving Referring Expressions in Images With Labeled Elements
Viaarxiv icon