11 citations · 26 across the 15 of their papers we have counts for
19 papers
Global Exponential Convergence of Two-Layer Linear Network Training
Stephen Y Zhang, Gabriel Peyré
We prove global exponential (linear) convergence with an explicit rate in the rich scaling for wide two-layer linear networks trained with smooth Polyak-Lojasiewicz predictor losse…
MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning
Revant Teotia, Adrien Bardes, Michael Rabbat +3
Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual streams naturally co-occur in vid…
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…
Beyond Language Modeling: An Exploration of Multimodal Pretraining
Shengbang Tong, David Fan, John Nguyen +18
The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models r…
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
Lorenzo Mur-Labadia, Matthew Muckley, Amir Bar +6
We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene under…
Inference-time Physics Alignment of Video Generative Models with Latent World Models
Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich +7
State-of-the-art video generative models produce promising visual content yet often violate basic physics principles, limiting their utility. While some attribute this deficiency t…
Learning Latent Action World Models In The Wild
Quentin Garrido, Tushar Nagarajan, Basile Terver +3
Agents capable of reasoning and planning in the real world require the ability of predicting the consequences of their actions. While world models possess this capability, they mos…
Improving the Physics of Video Generation with VJEPA-2 Reward Signal
Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich +7
This is a short technical report describing the winning entry of the PhysicsIQ Challenge, presented at the Perception Test Workshop at ICCV 2025. State-of-the-art video generative…
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…
Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
Aniket Didolkar, Nicolas Ballas, Sanjeev Arora +1
Large language models (LLMs) now solve multi-step problems by emitting extended chains of thought. During the process, they often re-derive the same intermediate steps across probl…
A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs
Benno Krojer, Mojtaba Komeili, Candace Ross +4
Existing benchmarks for assessing the spatio-temporal understanding and reasoning abilities of video language models are susceptible to score inflation due to the presence of short…
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
Mido Assran, Adrien Bardes, David Fan +27
A major challenge for modern AI is to learn to understand the world and learn to act largely by observation. This paper explores a self-supervised approach that combines internet-s…
Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D
Sergio Arnaud, Paul McVay, Ada Martin +19
We present LOCATE 3D, a model for localizing objects in 3D scenes from referring expressions like "the small coffee table between the sofa and the lamp." LOCATE 3D sets a new state…
Scaling Language-Free Visual Representation Learning
David Fan, Shengbang Tong, Jiachen Zhu +8
Visual Self-Supervised Learning (SSL) currently underperforms Contrastive Language-Image Pretraining (CLIP) in multimodal settings such as Visual Question Answering (VQA). This mul…
Intuitive physics understanding emerges from self-supervised pretraining on natural videos
Quentin Garrido, Nicolas Ballas, Mahmoud Assran +5
We investigate the emergence of intuitive physics understanding in general-purpose deep neural network models trained to predict masked regions in natural videos. Leveraging the vi…
VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning
Han Lin, Tushar Nagarajan, Nicolas Ballas +4
Procedural video representation learning is an active research area where the objective is to learn an agent which can anticipate and forecast the future given the present video in…
Modeling Caption Diversity in Contrastive Vision-Language Pretraining
Samuel Lavoie, Polina Kirichenko, Mark Ibrahim +4
There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting h…
Revisiting Feature Prediction for Learning Visual Representations from Video
Adrien Bardes, Quentin Garrido, Jean Ponce +5
This paper explores feature prediction as a stand-alone objective for unsupervised learning from video and introduces V-JEPA, a collection of vision models trained solely using a f…
Learning and Leveraging World Models in Visual Representation Learning
Quentin Garrido, Mahmoud Assran, Nicolas Ballas +3
Joint-Embedding Predictive Architecture (JEPA) has emerged as a promising self-supervised approach that learns by leveraging a world model. While previously limited to predicting m…