Sobal, Vlad

7 publications

ICLR 2025 $\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs Vlad Sobal, Mark Ibrahim, Randall Balestriero, Vivien Cabannes, Diane Bouchacourt, Pietro Astolfi, Kyunghyun Cho, Yann LeCun

ICLR 2025 Hierarchical World Models as Visual Whole-Body Humanoid Controllers Nicklas Hansen, S V Jyothir, Vlad Sobal, Yann LeCun, Xiaolong Wang, Hao Su

NeurIPS 2025 Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models Vlad Sobal, Wancong Zhang, Kyunghyun Cho, Randall Balestriero, Tim G. J. Rudner, Yann LeCun

ICLRW 2025 Stress-Testing Offline Reward-Free Reinforcement Learning: A Case for Planning with Latent Dynamics Models Vlad Sobal, Wancong Zhang, Kyunghyun Cho, Randall Balestriero, Tim G. J. Rudner, Yann LeCun

ICMLW 2024 $\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs Vlad Sobal, Mark Ibrahim, Randall Balestriero, Vivien Cabannes, Diane Bouchacourt, Pietro Astolfi, Kyunghyun Cho, Yann LeCun

NeurIPSW 2024 $\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs Vlad Sobal, Mark Ibrahim, Randall Balestriero, Vivien Cabannes, Diane Bouchacourt, Pietro Astolfi, Kyunghyun Cho, Yann LeCun

ICLRW 2022 Separating the World and Ego Models for Self-Driving Vlad Sobal, Alfredo Canziani, Nicolas Carion, Kyunghyun Cho, Yann LeCun