Picture for Ankit Anand

Ankit Anand

Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning

Add code
Apr 24, 2025
Viaarxiv icon

LearnLM: Improving Gemini for Learning

Add code
Dec 21, 2024
Viaarxiv icon

ReMI: A Dataset for Reasoning with Multiple Images

Add code
Jun 13, 2024
Figure 1 for ReMI: A Dataset for Reasoning with Multiple Images
Figure 2 for ReMI: A Dataset for Reasoning with Multiple Images
Figure 3 for ReMI: A Dataset for Reasoning with Multiple Images
Figure 4 for ReMI: A Dataset for Reasoning with Multiple Images
Viaarxiv icon

Code as Reward: Empowering Reinforcement Learning with VLMs

Add code
Feb 07, 2024
Figure 1 for Code as Reward: Empowering Reinforcement Learning with VLMs
Figure 2 for Code as Reward: Empowering Reinforcement Learning with VLMs
Figure 3 for Code as Reward: Empowering Reinforcement Learning with VLMs
Figure 4 for Code as Reward: Empowering Reinforcement Learning with VLMs
Viaarxiv icon

Transfer Learning for the Prediction of Entity Modifiers in Clinical Text: Application to Opioid Use Disorder Case Detection

Add code
Feb 05, 2024
Viaarxiv icon

GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoning

Add code
Dec 19, 2023
Viaarxiv icon

Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search

Add code
Nov 06, 2023
Figure 1 for Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
Figure 2 for Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
Figure 3 for Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
Figure 4 for Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
Viaarxiv icon

AutoMix: Automatically Mixing Language Models

Add code
Oct 19, 2023
Figure 1 for AutoMix: Automatically Mixing Language Models
Figure 2 for AutoMix: Automatically Mixing Language Models
Figure 3 for AutoMix: Automatically Mixing Language Models
Figure 4 for AutoMix: Automatically Mixing Language Models
Viaarxiv icon

Policy composition in reinforcement learning via multi-objective policy optimization

Add code
Aug 30, 2023
Viaarxiv icon

Accelerating exploration and representation learning with offline pre-training

Add code
Mar 31, 2023
Figure 1 for Accelerating exploration and representation learning with offline pre-training
Figure 2 for Accelerating exploration and representation learning with offline pre-training
Figure 3 for Accelerating exploration and representation learning with offline pre-training
Figure 4 for Accelerating exploration and representation learning with offline pre-training
Viaarxiv icon