7 citations · 25 across the 37 of their papers we have counts for
8 papers · 1 filter
Value-guided action planning with JEPA world models
Matthieu Destrade, Oumayma Bounou, Quentin Le Lidec +2
Building deep learning models that can reason about their environment requires capturing its underlying dynamics. Joint-Embedded Predictive Architectures (JEPA) provide a promising…
Closing the Train-Test Gap in World Models for Gradient-Based Planning
Arjun Parthasarathy, Nimit Kalra, Rohun Agrawal +4
World models paired with model predictive control (MPC) can be trained offline on large-scale datasets of expert trajectories and enable generalization to a wide range of planning…
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
Basile Terver, Tsung-Yen Yang, Jean Ponce +2
A long-standing challenge in AI is to develop agents capable of solving a wide range of physical tasks and generalizing to new, unseen tasks and environments. A popular recent appr…
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
Randall Balestriero, Yann LeCun
Learning manipulable representations of the world and its dynamics is central to AI. Joint-Embedding Predictive Architectures (JEPAs) offer a promising blueprint, but lack of pract…
Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
Randall Balestriero, Nicolas Ballas, Mike Rabbat +1
Joint Embedding Predictive Architectures (JEPAs) learn representations able to solve numerous downstream tasks out-of-the-box. JEPAs combine two objectives: (i) a latent-space pred…
LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
Hai Huang, Yann LeCun, Randall Balestriero
Large Language Model (LLM) pretraining, finetuning, and evaluation rely on input-space reconstruction and generative capabilities. Yet, it has been observed in vision that embeddin…
OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
Raktim Gautam Goswami, Prashanth Krishnamurthy, Yann LeCun +1
Visual imitation learning enables robotic agents to acquire skills by observing expert demonstration videos. In the one-shot setting, the agent generates a policy after observing a…
Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
Vlad Sobal, Wancong Zhang, Kyunghyun Cho +3
A long-standing goal in AI is to develop agents capable of solving diverse tasks across a range of environments, including those never seen during training. Two dominant paradigms…