Search Results for author:
Found 20 papers, 15 papers with code
Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training
Dramatic increases in the capabilities of neural network models in recent years are driven by scaling model size, training data, and corresponding computational resources.
Altogether: Image Captioning via Re-aligning Alt-text
This paper focuses on creating synthetic data to improve the quality of image captions.
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Our experiments show that Transfusion scales significantly better than quantizing images and training a language model over discrete image tokens.
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
We investigate efficient methods for training Large Language Models (LLMs) to possess capabilities in multiple specialized domains, such as coding, math reasoning and world knowledge.
Ranked #38 on
Common Sense Reasoning
on WinoGrande
TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
TorchAudio is an open-source audio and speech processing library built for PyTorch.
RA-DIT: Retrieval-Augmented Dual Instruction Tuning
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.
Ranked #21 on
Question Answering
on TriviaQA
(using extra training data)
The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment
In this work, we examine this phenomenon through a series of case studies analyzing the effects of model design decisions, framework paradigms, and hardware platforms on total model latency.
OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks
We present OLLA, an algorithm that optimizes the lifetime and memory location of the tensors used to train neural networks.
Reasoning over Public and Private Data in Retrieval-Based Systems
We first define the PUBLIC-PRIVATE AUTOREGRESSIVE INFORMATION RETRIEVAL (PAIR) privacy framework for the novel retrieval setting over multiple privacy scopes.
Ranked #1 on
Multi-hop Question Answering
on ConcurrentQA
Flashlight: Enabling Innovation in Tools for Machine Learning
This is in part due to the difficulties involved in prototyping new computational paradigms with existing frameworks.
Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
On a large-scale competitive setup, we show that pre-training on unlabeled in-domain data reduces the gap between models trained on in-domain and out-of-domain labeled data by 66%-73%.
Rethinking Evaluation in ASR: Are Our Models Robust Enough?
Finally, we show that training a single acoustic model on the most widely-used datasets - combined - reaches competitive performance on both research and real-world benchmarks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
SlimIPL: Language-Model-Free Iterative Pseudo-Labeling
We improve upon the IPL algorithm: as the model learns, we propose to iteratively re-generate transcriptions with hard labels (the most probable tokens), that is, without a language model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Differentiable Weighted Finite-State Transducers
We introduce a framework for automatic differentiation with weighted finite-state transducers (WFSTs) allowing them to be used dynamically at training time.
Iterative Pseudo-Labeling for Speech Recognition
In particular, IPL fine-tunes an existing model at each iteration using both labeled data and a subset of unlabeled data.
Ranked #13 on
Speech Recognition
on LibriSpeech test-other
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Scaling Up Online Speech Recognition Using ConvNets
We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC).
Libri-Light: A Benchmark for ASR with Limited or No Supervision
Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-supervised setting (PER, CER) and (3) the distant supervision setting (WER).
Ranked #1 on
Speech Recognition
on Libri-Light test-other
(ABX-within metric)
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
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 functions.
Ranked #19 on
Speech Recognition
on LibriSpeech test-other
(using extra training data)
Self-Training for End-to-End Speech Recognition
We revisit self-training in the context of end-to-end speech recognition.
wav2letter++: The Fastest Open-source Speech Recognition System
This paper introduces wav2letter++, the fastest open-source deep learning speech recognition framework.
