Picture for Jitendra Malik

Jitendra Malik

OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction

Add code
Mar 05, 2025
Viaarxiv icon

Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids

Add code
Feb 27, 2025
Viaarxiv icon

Poly-Autoregressive Prediction for Modeling Interactions

Add code
Feb 12, 2025
Viaarxiv icon

DexterityGen: Foundation Controller for Unprecedented Dexterity

Add code
Feb 06, 2025
Figure 1 for DexterityGen: Foundation Controller for Unprecedented Dexterity
Figure 2 for DexterityGen: Foundation Controller for Unprecedented Dexterity
Figure 3 for DexterityGen: Foundation Controller for Unprecedented Dexterity
Figure 4 for DexterityGen: Foundation Controller for Unprecedented Dexterity
Viaarxiv icon

An Empirical Study of Autoregressive Pre-training from Videos

Add code
Jan 09, 2025
Figure 1 for An Empirical Study of Autoregressive Pre-training from Videos
Figure 2 for An Empirical Study of Autoregressive Pre-training from Videos
Figure 3 for An Empirical Study of Autoregressive Pre-training from Videos
Figure 4 for An Empirical Study of Autoregressive Pre-training from Videos
Viaarxiv icon

From Simple to Complex Skills: The Case of In-Hand Object Reorientation

Add code
Jan 09, 2025
Viaarxiv icon

Gaussian Masked Autoencoders

Add code
Jan 06, 2025
Figure 1 for Gaussian Masked Autoencoders
Figure 2 for Gaussian Masked Autoencoders
Figure 3 for Gaussian Masked Autoencoders
Figure 4 for Gaussian Masked Autoencoders
Viaarxiv icon

Reconstructing People, Places, and Cameras

Add code
Dec 23, 2024
Viaarxiv icon

Learning from Massive Human Videos for Universal Humanoid Pose Control

Add code
Dec 18, 2024
Figure 1 for Learning from Massive Human Videos for Universal Humanoid Pose Control
Figure 2 for Learning from Massive Human Videos for Universal Humanoid Pose Control
Figure 3 for Learning from Massive Human Videos for Universal Humanoid Pose Control
Figure 4 for Learning from Massive Human Videos for Universal Humanoid Pose Control
Viaarxiv icon

Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment

Add code
Dec 06, 2024
Figure 1 for Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
Figure 2 for Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
Figure 3 for Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
Figure 4 for Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
Viaarxiv icon