Picture for Luca Weihs

Luca Weihs

MutaGReP: Execution-Free Repository-Grounded Plan Search for Code-Use

Add code
Feb 21, 2025
Viaarxiv icon

Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation

Add code
Feb 20, 2025
Viaarxiv icon

The One RING: a Robotic Indoor Navigation Generalist

Add code
Dec 18, 2024
Viaarxiv icon

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Add code
Sep 25, 2024
Figure 1 for Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Figure 2 for Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Figure 3 for Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Figure 4 for Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Viaarxiv icon

PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators

Add code
Jun 28, 2024
Figure 1 for PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators
Figure 2 for PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators
Figure 3 for PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators
Figure 4 for PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators
Viaarxiv icon

CodeNav: Beyond tool-use to using real-world codebases with LLM agents

Add code
Jun 18, 2024
Figure 1 for CodeNav: Beyond tool-use to using real-world codebases with LLM agents
Figure 2 for CodeNav: Beyond tool-use to using real-world codebases with LLM agents
Figure 3 for CodeNav: Beyond tool-use to using real-world codebases with LLM agents
Figure 4 for CodeNav: Beyond tool-use to using real-world codebases with LLM agents
Viaarxiv icon

Seeing the Unseen: Visual Common Sense for Semantic Placement

Add code
Jan 15, 2024
Figure 1 for Seeing the Unseen: Visual Common Sense for Semantic Placement
Figure 2 for Seeing the Unseen: Visual Common Sense for Semantic Placement
Figure 3 for Seeing the Unseen: Visual Common Sense for Semantic Placement
Figure 4 for Seeing the Unseen: Visual Common Sense for Semantic Placement
Viaarxiv icon

Holodeck: Language Guided Generation of 3D Embodied AI Environments

Add code
Dec 14, 2023
Viaarxiv icon

Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences

Add code
Dec 14, 2023
Figure 1 for Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences
Figure 2 for Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences
Figure 3 for Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences
Figure 4 for Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences
Viaarxiv icon

Understanding Representations Pretrained with Auxiliary Losses for Embodied Agent Planning

Add code
Dec 06, 2023
Viaarxiv icon