papers

Publications (68)

cs.CL2025

ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Jiarui Lu, Thomas Holleis, Yizhe Zhang +9

Recent large language models (LLMs) advancements sparked a growing research interest in tool assisted LLMs solving real-world challenges, which calls for comprehensive evaluation o…

cs.LG2025

RLAX: Large-Scale, Distributed Reinforcement Learning for Large Language Models on TPUs

Runlong Zhou, Lefan Zhang, Shang-Chen Wu +29

Reinforcement learning (RL) has emerged as the de-facto paradigm for improving the reasoning capabilities of large language models (LLMs). We have developed RLAX, a scalable RL fra…

cs.LG2025

Apple Intelligence Foundation Language Models: Tech Report 2025

Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang +395

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model opti…

cs.CV2020

EfficientDet: Scalable and Efficient Object Detection

Mingxing Tan, Ruoming Pang, Quoc V. Le

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and pr…

cs.CV2018

Domain Adaptive Transfer Learning with Specialist Models

Jiquan Ngiam, Daiyi Peng, Vijay Vasudevan +3

Transfer learning is a widely used method to build high performing computer vision models. In this paper, we study the efficacy of transfer learning by examining how the choice of…

eess.AS2020

Conformer: Convolution-augmented Transformer for Speech Recognition

Anmol Gulati, James Qin, Chung-Cheng Chiu +8

Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (…

cs.DC2022

Pathways: Asynchronous Distributed Dataflow for ML

Paul Barham, Aakanksha Chowdhery, Jeff Dean +13

We present the design of a new large scale orchestration layer for accelerators. Our system, Pathways, is explicitly designed to enable exploration of new systems and ML research i…

cs.CV2021

Co-training Transformer with Videos and Images Improves Action Recognition

Bowen Zhang, Jiahui Yu, Christopher Fifty +4

In learning action recognition, models are typically pre-trained on object recognition with images, such as ImageNet, and later fine-tuned on target action recognition with videos.…

cs.LG2026

AXLearn: Modular, Hardware-Agnostic Large Model Training

Mark Lee, Chang Lan, Tom Gunter +34

AXLearn is a production system which facilitates scalable and high-performance training of large deep learning models. Compared to other state-of-art deep learning systems, AXLearn…

cs.CV2023

Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts

Erik Daxberger, Floris Weers, Bowen Zhang +7

Sparse Mixture-of-Experts models (MoEs) have recently gained popularity due to their ability to decouple model size from inference efficiency by only activating a small subset of t…

cs.CV2025

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Yanghao Li, Rui Qian, Bowen Pan +24

Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from…

cs.LG2019

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

Jonathan Shen, Patrick Nguyen, Yonghui Wu +88

Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models a…

cs.LG2021

W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training

Yu-An Chung, Yu Zhang, Wei Han +4

Motivated by the success of masked language modeling~(MLM) in pre-training natural language processing models, we propose w2v-BERT that explores MLM for self-supervised speech repr…

eess.AS2021

Dynamic Sparsity Neural Networks for Automatic Speech Recognition

Zhaofeng Wu, Ding Zhao, Qiao Liang +3

In automatic speech recognition (ASR), model pruning is a widely adopted technique that reduces model size and latency to deploy neural network models on edge devices with resource…

cs.CL2021

Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling

Jiahui Yu, Wei Han, Anmol Gulati +5

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full sp…

cs.CL2025

RATTENTION: Towards the Minimal Sliding Window Size in Local-Global Attention Models

Bailin Wang, Chang Lan, Chong Wang +1

Local-global attention models have recently emerged as compelling alternatives to standard Transformers, promising improvements in both training and inference efficiency. However,…

cs.CL2021

Unsupervised Learning of Disentangled Speech Content and Style Representation

Andros Tjandra, Ruoming Pang, Yu Zhang +1

We present an approach for unsupervised learning of speech representation disentangling contents and styles. Our model consists of: (1) a local encoder that captures per-frame info…

cs.LG2025

Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations

Ajay Jaiswal, Jianyu Wang, Yixiao Li +6

Sparsely activated Mixture-of-Experts (SMoE) has shown promise in scaling up the learning capacity of neural networks. However, vanilla SMoEs have issues such as expert redundancy…

eess.AS2020

Cascaded encoders for unifying streaming and non-streaming ASR

Arun Narayanan, Tara N. Sainath, Ruoming Pang +5

End-to-end (E2E) automatic speech recognition (ASR) models, by now, have shown competitive performance on several benchmarks. These models are structured to either operate in strea…

eess.AS2020

ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context

Wei Han, Zhengdong Zhang, Yu Zhang +6

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper…

cs.CL2018

Hierarchical Generative Modeling for Controllable Speech Synthesis

Wei-Ning Hsu, Yu Zhang, Ron J. Weiss +9

This paper proposes a neural sequence-to-sequence text-to-speech (TTS) model which can control latent attributes in the generated speech that are rarely annotated in the training d…

cs.CV2022

Vector-quantized Image Modeling with Improved VQGAN

Jiahui Yu, Xin Li, Jing Yu Koh +7

Pretraining language models with next-token prediction on massive text corpora has delivered phenomenal zero-shot, few-shot, transfer learning and multi-tasking capabilities on bot…

cs.SD2021

Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data

Thibault Doutre, Wei Han, Min Ma +7

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech wi…

cs.CV2024

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier +29

In this work, we discuss building performant Multimodal Large Language Models (MLLMs). In particular, we study the importance of various architecture components and data choices. T…

eess.AS2022

BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition

Yu Zhang, Daniel S. Park, Wei Han +23

We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a m…

cs.CL2025

Reusing Pre-Training Data at Test Time is a Compute Multiplier

Alex Fang, Thomas Voice, Ruoming Pang +2

Large language models learn from their vast pre-training corpora, gaining the ability to solve an ever increasing variety of tasks; yet although researchers work to improve these d…

cs.LG2025

Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo

Shengyu Feng, Xiang Kong, Shuang Ma +5

Augmenting the multi-step reasoning abilities of Large Language Models (LLMs) has been a persistent challenge. Recently, verification has shown promise in improving solution consis…

cs.CV2023

STAIR: Learning Sparse Text and Image Representation in Grounded Tokens

Chen Chen, Bowen Zhang, Liangliang Cao +7

Image and text retrieval is one of the foundational tasks in the vision and language domain with multiple real-world applications. State-of-the-art approaches, e.g. CLIP, ALIGN, re…

eess.AS2020

RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions

Chung-Cheng Chiu, Arun Narayanan, Wei Han +8

In recent years, all-neural end-to-end approaches have obtained state-of-the-art results on several challenging automatic speech recognition (ASR) tasks. However, most existing wor…

cs.DC2026

ScaleAcross Explorer: Exploring Communication Optimization for Scale-Across AI Model Training

Minghao Li, Alicia Golden, Samuel Hsia +14

The rapid scaling of large language model training requires distributing GPU resources across multiple data center buildings and regions. We refer to such paradigm as "scale-across…

cs.CV2019

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang +1

Current state-of-the-art convolutional architectures for object detection are manually designed. Here we aim to learn a better architecture of feature pyramid network for object de…

cs.CL2025

Instruction-Following Pruning for Large Language Models

Bairu Hou, Qibin Chen, Jianyu Wang +6

With the rapid scaling of large language models (LLMs), structured pruning has become a widely used technique to learn efficient, smaller models from larger ones, delivering superi…

cs.CV2021

Searching for Fast Model Families on Datacenter Accelerators

Sheng Li, Mingxing Tan, Ruoming Pang +4

Neural Architecture Search (NAS), together with model scaling, has shown remarkable progress in designing high accuracy and fast convolutional architecture families. However, as ne…

cs.DC2021

GSPMD: General and Scalable Parallelization for ML Computation Graphs

Yuanzhong Xu, HyoukJoong Lee, Dehao Chen +13

We present GSPMD, an automatic, compiler-based parallelization system for common machine learning computations. It allows users to write programs in the same way as for a single de…

eess.AS2020

Towards Fast and Accurate Streaming End-to-End ASR

Bo Li, Shuo-yiin Chang, Tara N. Sainath +4

End-to-end (E2E) models fold the acoustic, pronunciation and language models of a conventional speech recognition model into one neural network with a much smaller number of parame…

eess.AS2021

FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization

Jiahui Yu, Chung-Cheng Chiu, Bo Li +8

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measure…

cs.CL2025

Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics

Siddhant Arora, Zhiyun Lu, Chung-Cheng Chiu +2

The recent wave of audio foundation models (FMs) could provide new capabilities for conversational modeling. However, there have been limited efforts to evaluate these audio FMs co…

cs.DC2026

Parallel Track Transformers: Enabling Fast GPU Inference with Reduced Synchronization

Chong Wang, Nan Du, Tom Gunter +8

Efficient large-scale inference of transformer-based large language models (LLMs) remains a fundamental systems challenge, frequently requiring multi-GPU parallelism to meet string…

cs.CV2020

BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models

Jiahui Yu, Pengchong Jin, Hanxiao Liu +7

Neural architecture search (NAS) has shown promising results discovering models that are both accurate and fast. For NAS, training a one-shot model has become a popular strategy to…

cs.AI2026

Apple Intelligence Foundation Language Models

Tom Gunter, Zirui Wang, Chong Wang +152

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large serv…

eess.AS2022

Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition

Yu Zhang, James Qin, Daniel S. Park +5

We employ a combination of recent developments in semi-supervised learning for automatic speech recognition to obtain state-of-the-art results on LibriSpeech utilizing the unlabele…

cs.LG2024

Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training

Xianzhi Du, Tom Gunter, Xiang Kong +5

Mixture-of-Experts (MoE) enjoys performance gain by increasing model capacity while keeping computation cost constant. When comparing MoE to dense models, prior work typically adop…

eess.AS2019

A comparison of end-to-end models for long-form speech recognition

Chung-Cheng Chiu, Wei Han, Yu Zhang +11

End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance com…

cs.CL2019

Monotonic Infinite Lookback Attention for Simultaneous Machine Translation

Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey +5

Simultaneous machine translation begins to translate each source sentence before the source speaker is finished speaking, with applications to live and streaming scenarios. Simulta…

eess.AS2021

A Better and Faster End-to-End Model for Streaming ASR

Bo Li, Anmol Gulati, Jiahui Yu +12

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by…

eess.AS2022

A Language Agnostic Multilingual Streaming On-Device ASR System

Bo Li, Tara N. Sainath, Ruoming Pang +9

On-device end-to-end (E2E) models have shown improvements over a conventional model on English Voice Search tasks in both quality and latency. E2E models have also shown promising…

cs.CL2018

Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions

Jonathan Shen, Ruoming Pang, Ron J. Weiss +10

This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature predictio…

cs.CL2021

Transformer Based Deliberation for Two-Pass Speech Recognition

Ke Hu, Ruoming Pang, Tara N. Sainath +1

Interactive speech recognition systems must generate words quickly while also producing accurate results. Two-pass models excel at these requirements by employing a first-pass deco…

eess.AS2020

Deliberation Model Based Two-Pass End-to-End Speech Recognition

Ke Hu, Tara N. Sainath, Ruoming Pang +1

End-to-end (E2E) models have made rapid progress in automatic speech recognition (ASR) and perform competitively relative to conventional models. To further improve the quality, a…

cs.CL2025

Synthetic bootstrapped pretraining

Zitong Yang, Aonan Zhang, Hong Liu +4

We introduce Synthetic Bootstrapped Pretraining (SBP), a language model (LM) pretraining procedure that first learns a model of relations between documents from the pretraining dat…

cs.CL2018

Streaming End-to-end Speech Recognition For Mobile Devices

Yanzhang He, Tara N. Sainath, Rohit Prabhavalkar +17

End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present nu…

cs.CV2019

MnasNet: Platform-Aware Neural Architecture Search for Mobile

Mingxing Tan, Bo Chen, Ruoming Pang +4

Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts ha…

cs.CL2019

Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

Ye Jia, Yu Zhang, Ron J. Weiss +8

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen d…

cs.CL2019

Two-Pass End-to-End Speech Recognition

Tara N. Sainath, Ruoming Pang, David Rybach +9

The requirements for many applications of state-of-the-art speech recognition systems include not only low word error rate (WER) but also low latency. Specifically, for many use-ca…

cs.CL2023

Practical Conformer: Optimizing size, speed and flops of Conformer for on-Device and cloud ASR

Rami Botros, Anmol Gulati, Tara N. Sainath +5

Conformer models maintain a large number of internal states, the vast majority of which are associated with self-attention layers. With limited memory bandwidth, reading these from…

cs.CV2025

EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing

Haotian Sun, Tao Lei, Bowen Zhang +5

Diffusion transformers have been widely adopted for text-to-image synthesis. While scaling these models up to billions of parameters shows promise, the effectiveness of scaling bey…

cs.AI2024

MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains

Guoli Yin, Haoping Bai, Shuang Ma +21

Recent advances in large language models (LLMs) have increased the demand for comprehensive benchmarks to evaluate their capabilities as human-like agents. Existing benchmarks, whi…

cs.CL2020

A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency

Tara N. Sainath, Yanzhang He, Bo Li +26

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e…

eess.AS2020

Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition

Wei Li, James Qin, Chung-Cheng Chiu +2

Recent advances of end-to-end models have outperformed conventional models through employing a two-pass model. The two-pass model provides better speed-quality trade-offs for on-de…

cs.CV2019

Searching for MobileNetV3

Andrew Howard, Mark Sandler, Grace Chu +9

We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design. MobileNetV3 is tuned to mobile phone…

cs.CL2024

Large Language Model-guided Document Selection

Xiang Kong, Tom Gunter, Ruoming Pang

Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quali…

cs.CL2023

Instruction-Following Speech Recognition

Cheng-I Jeff Lai, Zhiyun Lu, Liangliang Cao +1

Conventional end-to-end Automatic Speech Recognition (ASR) models primarily focus on exact transcription tasks, lacking flexibility for nuanced user interactions. With the advent o…

cs.AI2024

Improve Vision Language Model Chain-of-thought Reasoning

Ruohong Zhang, Bowen Zhang, Yanghao Li +6

Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT r…

cs.CL2021

Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models

Thibault Doutre, Wei Han, Chung-Cheng Chiu +3

Streaming end-to-end automatic speech recognition (ASR) systems are widely used in everyday applications that require transcribing speech to text in real-time. Their minimal latenc…

cs.CL2022

Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition

W. Ronny Huang, Cal Peyser, Tara N. Sainath +3

Language model fusion helps smart assistants recognize words which are rare in acoustic data but abundant in text-only corpora (typed search logs). However, such corpora have prope…

eess.AS2020

Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpus

Cal Peyser, Sepand Mavandadi, Tara N. Sainath +3

End-to-end (E2E) automatic speech recognition (ASR) systems lack the distinct language model (LM) component that characterizes traditional speech systems. While this simplifies the…

cs.CL2025

Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge?

Arduin Findeis, Floris Weers, Guoli Yin +3

Pairwise preferences over model responses are widely collected to evaluate and provide feedback to large language models (LLMs). Given two alternative model responses to the same i…

cs.CL2021

Scaling End-to-End Models for Large-Scale Multilingual ASR

Bo Li, Ruoming Pang, Tara N. Sainath +7

Building ASR models across many languages is a challenging multi-task learning problem due to large variations and heavily unbalanced data. Existing work has shown positive transfe…