10 citations · 21 across the 7 of their papers we have counts for
8 papers
H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning
Wancong Zhang, Basile Terver, Michael Rabbat +2
Long-horizon planning with latent world models requires reasoning across timescales and levels of abstraction. Existing task-agnostic JEPA world models predict and plan at a single…
SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors
Pratyaksh Rao, Wancong Zhang, Randall Balestriero +2
Accurate dynamics models are critical for informed decision-making in robotic systems, particularly for agile aerial vehicles operating under uncertainty. Neural network dynamics m…
Hierarchical Planning with Latent World Models
Wancong Zhang, Basile Terver, Artem Zholus +8
World models are a promising path to zero-shot embodied control through planning. However, existing world model planners struggle on long-horizon, multi-stage tasks: prediction err…
A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
Basile Terver, Randall Balestriero, Megi Dervishi +8
We present EB-JEPA, an open-source library for learning representations and world models using Joint-Embedding Predictive Architectures (JEPAs). JEPAs learn to predict in represent…
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…
Light-weight probing of unsupervised representations for Reinforcement Learning
Wancong Zhang, Anthony GX-Chen, Vlad Sobal +2
Unsupervised visual representation learning offers the opportunity to leverage large corpora of unlabeled trajectories to form useful visual representations, which can benefit the…
MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture
Wancong Zhang, Ieshan Vaidya
MixUp is a computer vision data augmentation technique that uses convex interpolations of input data and their labels to enhance model generalization during training. However, the…
A Comprehensive Evaluation of Multi-task Learning and Multi-task Pre-training on EHR Time-series Data
Matthew B. A. McDermott, Bret Nestor, Evan Kim +4
Multi-task learning (MTL) is a machine learning technique aiming to improve model performance by leveraging information across many tasks. It has been used extensively on various d…