22 citations · 107 across the 37 of their papers we have counts for
44 papers
SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision
Junyan Jiang, Ruibin Yuan, Jiahao Pan +4
Transcribing music into a human-readable score requires a coherent understanding of rhythm, harmony, melody, and form. Two obstacles limit this goal: annotated recordings are scarc…
Learning Functional Subspaces for Neural Network Compression
Massimo Bini, Anders Christensen, Stephan Alaniz +5
Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping the matrices dense, and thus…
SCOPE: Observation-Conditioned Full-Target Prediction for Sparse PDE Inference
Ruichen Xu, Siyao Wang, Fang Wan +8
Recovering complete physical fields from sparse observations is challenging because the measurements may not uniquely determine the underlying state. Diffusion-based PDE solvers ad…
PDE-OBS: Controlled Evaluation Across Observation Patterns
Ruichen Xu, Siyao Wang, Fang Wan +7
Physical-field reconstruction and forecasting depend on both measurement density and spatial layout, yet evaluation under a single observation pattern does not characterize perform…
HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning
Ruichen Xu, Jingxiang Qu, Wenhan Gao +5
Graph self-supervised learning aims to learn transferable representations from large-scale unlabeled graph data. Joint-embedding predictive architectures (JEPAs) avoid explicit neg…
Separating Representation from Reconstruction Enables Scalable Text Encoders
Megi Dervishi, Mathurin Videau, Yann LeCun
While decoders have rapidly scaled, encoders have remained largely unchanged since BERT. We revisit this disparity by frozen backbone evaluation via probing. Under this lens, the r…
Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement
Nian Liu, Nikita Kazeev, Stephen Gregory Dale +8
De novo crystal generation seeks to discover materials that are not merely realistic, but also stable and novel. However, most existing generative models are trained to maximize th…
The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
Shangwen Sun, Alfredo Canziani, Yann LeCun +1
We study two recurring phenomena in Transformer language models: massive activations, in which a small number of tokens exhibit extreme outliers in a few channels, and attention si…
AI+HW 2035: Shaping the Next Decade
Deming Chen, Jason Cong, Azalia Mirhoseini +27
Artificial intelligence (AI) and hardware (HW) are advancing at unprecedented rates, yet their trajectories have become inseparably intertwined. The global research community lacks…
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…
AI Must Embrace Specialization via Superhuman Adaptable Intelligence
Judah Goldfeder, Philippe Wyder, Yann LeCun +1
Everyone from AI executives and researchers to doomsayers, politicians, and activists is talking about Artificial General Intelligence (AGI). Yet, they often don't seem to agree on…
Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA
Hai Huang, Yann LeCun, Randall Balestriero
Large Language Models (LLMs) obey consistent scaling laws -- empirical power-law fits that predict how loss decreases with compute, data, and parameters. While predictive, these la…
Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures
Georgios Ioannides, Adrian Kieback, Judah Goldfeder +5
Joint Embedding Predictive Architectures (JEPA) offer a promising approach to self-supervised speech representation learning, but suffer from representation collapse without explic…
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
Shengbang Tong, Boyang Zheng, Ziteng Wang +7
Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet by training in high-dimensional semantic latent spaces. In this work, we investi…
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…
JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention
Georgios Ioannides, Christos Constantinou, Aman Chadha +4
We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning…
SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation
Mahi Luthra, Jiayi Shen, Maxime Poli +14
Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compared to the data-hungry self-super…
Cambrian-S: Towards Spatial Supersensing in Video
Shusheng Yang, Jihan Yang, Pinzhi Huang +12
We argue that progress in true multimodal intelligence calls for a shift from reactive, task-driven systems and brute-force long context towards a broader paradigm of supersensing.…
Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
Enrique Queipo-de-Llano, Álvaro Arroyo, Federico Barbero +4
Attention sinks and compression valleys have attracted significant attention as two puzzling phenomena in large language models, but have been studied in isolation. In this work, w…
Back to the Features: DINO as a Foundation for Video World Models
Federico Baldassarre, Marc Szafraniec, Basile Terver +6
We present DINO-world, a powerful generalist video world model trained to predict future frames in the latent space of DINOv2. By leveraging a pre-trained image encoder and trainin…
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…
From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
Chen Shani, Liron Soffer, Dan Jurafsky +2
Humans organize knowledge into compact conceptual categories that balance compression with semantic richness. Large Language Models (LLMs) exhibit impressive linguistic abilities,…
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…
Transformers without Normalization
Jiachen Zhu, Xinlei Chen, Kaiming He +2
Normalization layers are ubiquitous in modern neural networks and have long been considered essential. This work demonstrates that Transformers without normalization can achieve th…