papers

Publications (25)

cs.LG2023

The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment

Jared Fernandez, Jacob Kahn, Clara Na +2

Increased focus on the computational efficiency of NLP systems has motivated the design of efficient model architectures and improvements to underlying hardware accelerators. Howev…

cs.CL2019

Libri-Light: A Benchmark for ASR with Limited or No Supervision

Jacob Kahn, Morgane Rivière, Weiyi Zheng +12

We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books f…

cs.CL2020

Scaling Up Online Speech Recognition Using ConvNets

Vineel Pratap, Qiantong Xu, Jacob Kahn +6

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS a…

cs.SD2021

Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training

Wei-Ning Hsu, Anuroop Sriram, Alexei Baevski +8

Self-supervised learning of speech representations has been a very active research area but most work is focused on a single domain such as read audio books for which there exist l…

cs.AI2024

Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Chunting Zhou, Lili Yu, Arun Babu +7

We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token predicti…

cs.LG2022

Flashlight: Enabling Innovation in Tools for Machine Learning

Jacob Kahn, Vineel Pratap, Tatiana Likhomanenko +11

As the computational requirements for machine learning systems and the size and complexity of machine learning frameworks increases, essential framework innovation has become chall…

cs.SE2025

CWM: An Open-Weights LLM for Research on Code Generation with World Models

FAIR CodeGen team, Jade Copet, Quentin Carbonneaux +48

We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can…

cs.CL2024

RA-DIT: Retrieval-Augmented Dual Instruction Tuning

Xi Victoria Lin, Xilun Chen, Mingda Chen +9

Retrieval-augmented language models (RALMs) improve performance by accessing long-tail and up-to-date knowledge from external data stores, but are challenging to build. Existing ap…

cs.CL2020

End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures

Gabriel Synnaeve, Qiantong Xu, Jacob Kahn +6

We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functio…

cs.SE2026

Code World Model Preparedness Report

Daniel Song, Peter Ney, Cristina Menghini +21

This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conducted pre-release testing across…

cs.LG2025

Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training

Jared Fernandez, Luca Wehrstedt, Leonid Shamis +5

Dramatic increases in the capabilities of neural network models in recent years are driven by scaling model size, training data, and corresponding computational resources. To devel…

cs.CL2021

SlimIPL: Language-Model-Free Iterative Pseudo-Labeling

Tatiana Likhomanenko, Qiantong Xu, Jacob Kahn +2

Recent results in end-to-end automatic speech recognition have demonstrated the efficacy of pseudo-labeling for semi-supervised models trained both with Connectionist Temporal Clas…

cs.CL2020

Iterative Pseudo-Labeling for Speech Recognition

Qiantong Xu, Tatiana Likhomanenko, Jacob Kahn +3

Pseudo-labeling has recently shown promise in end-to-end automatic speech recognition (ASR). We study Iterative Pseudo-Labeling (IPL), a semi-supervised algorithm which efficiently…

cs.CV2024

Altogether: Image Captioning via Re-aligning Alt-text

Hu Xu, Po-Yao Huang, Xiaoqing Ellen Tan +10

This paper focuses on creating synthetic data to improve the quality of image captions. Existing works typically have two shortcomings. First, they caption images from scratch, ign…

cs.LG2025

Characterizing and Efficiently Accelerating Multimodal Generation Model Inference

Yejin Lee, Anna Sun, Basil Hosmer +27

Generative artificial intelligence (AI) technology is revolutionizing the computing industry. Not only its applications have broadened to various sectors but also poses new system…

cs.DC2026

PRISM: Evaluating POSIX Storage Systems for AI Research Workflows

Adithya Kumar, Aditya Basu, Jacob Kahn +3

The rapid advancement of AI research is driven by massive investments in GPU clusters, yet the critical role of storage systems in enabling efficient research workflows is often ov…

cs.LG2022

OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks

Benoit Steiner, Mostafa Elhoushi, Jacob Kahn +1

The size of deep neural networks has grown exponentially in recent years. Unfortunately, hardware devices have not kept pace with the rapidly increasing memory requirements. To cop…

cs.CL2024

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM

Sainbayar Sukhbaatar, Olga Golovneva, Vasu Sharma +8

We investigate efficient methods for training Large Language Models (LLMs) to possess capabilities in multiple specialized domains, such as coding, math reasoning and world knowled…

cs.IR2022

Reasoning over Public and Private Data in Retrieval-Based Systems

Simran Arora, Patrick Lewis, Angela Fan +2

Users and organizations are generating ever-increasing amounts of private data from a wide range of sources. Incorporating private data is important to personalize open-domain appl…

eess.AS2023

TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch

Jeff Hwang, Moto Hira, Caroline Chen +21

TorchAudio is an open-source audio and speech processing library built for PyTorch. It aims to accelerate the research and development of audio and speech technologies by providing…

cs.LG2020

Differentiable Weighted Finite-State Transducers

Awni Hannun, Vineel Pratap, Jacob Kahn +1

We introduce a framework for automatic differentiation with weighted finite-state transducers (WFSTs) allowing them to be used dynamically at training time. Through the separation…

cs.LG2021

Rethinking Evaluation in ASR: Are Our Models Robust Enough?

Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap +5

Is pushing numbers on a single benchmark valuable in automatic speech recognition? Research results in acoustic modeling are typically evaluated based on performance on a single da…

cs.DC2025

Agentic Operator Generation for ML ASICs

Alec M. Hammond, Aram Markosyan, Aman Dontula +15

We present TritorX, an agentic AI system designed to generate functionally correct Triton PyTorch ATen kernels at scale for emerging accelerator platforms. TritorX integrates open-…

cs.CL2020

Self-Training for End-to-End Speech Recognition

Jacob Kahn, Ann Lee, Awni Hannun

We revisit self-training in the context of end-to-end speech recognition. We demonstrate that training with pseudo-labels can substantially improve the accuracy of a baseline model…

cs.CL2018

wav2letter++: The Fastest Open-source Speech Recognition System

Vineel Pratap, Awni Hannun, Qiantong Xu +5

This paper introduces wav2letter++, the fastest open-source deep learning speech recognition framework. wav2letter++ is written entirely in C++, and uses the ArrayFire tensor libra…