English
Related papers

Related papers: Turbo Training with Token Dropout

200 papers

In this work, we investigate the potential of improving multi-task training and also leveraging it for transferring in the reinforcement learning setting. We identify several challenges towards this goal and propose a transferring approach…

Robotics · Computer Science 2023-06-06 Lingfeng Sun , Haichao Zhang , Wei Xu , Masayoshi Tomizuka

With the emergence of large model-based agents, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which may result in high bandwidth overhead, increased power consumption…

Networking and Internet Architecture · Computer Science 2025-11-04 Junhe Zhang , Wanli Ni , Pengwei Wang , Dongyu Wang

The impressive performance of deep learning architectures is associated with a massive increase in model complexity. Millions of parameters need to be tuned, with training and inference time scaling accordingly, together with energy…

Machine Learning · Computer Science 2023-11-10 Paolo Didier Alfano , Vito Paolo Pastore , Lorenzo Rosasco , Francesca Odone

Deep Learning has revolutionized machine learning and artificial intelligence, achieving superhuman performance in several standard benchmarks. It is well-known that deep learning models are inefficient to train; they learn by processing…

Machine Learning · Computer Science 2021-12-03 Fartash Faghri

This article describes our experiments in neural machine translation using the recent Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et al., 2017). We examine some of the critical parameters that affect the…

Computation and Language · Computer Science 2018-05-03 Martin Popel , Ondřej Bojar

We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are then encoded by a series of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Anurag Arnab , Mostafa Dehghani , Georg Heigold , Chen Sun , Mario Lučić , Cordelia Schmid

Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in real-world scenarios. To achieve…

Computer Vision and Pattern Recognition · Computer Science 2023-12-13 Chen Ju , Haicheng Wang , Zeqian Li , Xu Chen , Zhonghua Zhai , Weilin Huang , Shuai Xiao

Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in the real-world scenarios. To achieve…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Chen Ju , Haicheng Wang , Haozhe Cheng , Xu Chen , Zhonghua Zhai , Weilin Huang , Jinsong Lan , Shuai Xiao , Bo Zheng

In this paper, we study the Tiered Reinforcement Learning setting, a parallel transfer learning framework, where the goal is to transfer knowledge from the low-tier (source) task to the high-tier (target) task to reduce the exploration risk…

Machine Learning · Computer Science 2024-06-14 Jiawei Huang , Niao He

We empirically study autoregressive pre-training from videos. To perform our study, we construct a series of autoregressive video models, called Toto. We treat videos as sequences of visual tokens and train transformer models to…

Computer Vision and Pattern Recognition · Computer Science 2025-01-10 Jathushan Rajasegaran , Ilija Radosavovic , Rahul Ravishankar , Yossi Gandelsman , Christoph Feichtenhofer , Jitendra Malik

The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…

Computation and Language · Computer Science 2025-09-30 Yijun Tian , Shaoyu Chen , Zhichao Xu , Yawei Wang , Jinhe Bi , Peng Han , Wei Wang

Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Biao Chen , Lin Zuo , Mengmeng Jing , Kunbin He , Yuchen Wang

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for…

Machine Learning · Computer Science 2018-07-12 Veronica Morfi , Dan Stowell

Training large transformer models is one of the most important computational challenges of modern AI. In this paper, we show how to significantly accelerate training of large transformer models by reducing activation recomputation.…

Machine Learning · Computer Science 2022-05-12 Vijay Korthikanti , Jared Casper , Sangkug Lym , Lawrence McAfee , Michael Andersch , Mohammad Shoeybi , Bryan Catanzaro

A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task. Transfer learning proposes to address this issue by re-using knowledge from previously…

Machine Learning · Computer Science 2023-04-28 Remo Sasso , Matthia Sabatelli , Marco A. Wiering

Deep convolutional neural network has made huge revolution and shown its superior performance on computer vision tasks such as classification and segmentation. Recent years, researches devote much effort to scaling down size of network…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Yingdong Hu

Most of the learning-based algorithms for bitrate adaptation are limited to offline learning, which inevitably suffers from the simulation-to-reality gap. Online learning can better adapt to dynamic real-time communication scenes but still…

Multimedia · Computer Science 2023-08-22 Qianyuan Zheng , Hao Chen , Zhan Ma

Training strong video generation models usually requires massive datasets, large parameter counts, and substantial compute. In this work, we ask whether strong text-to-video quality is possible at a much smaller budget: fewer than 10M clips…

Self-supervised tasks have been utilized to build useful representations that can be used in downstream tasks when the annotation is unavailable. In this paper, we introduce a self-supervised video representation learning method based on…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Duc Quang Vu , Ngan T. H. Le , Jia-Ching Wang

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers. It can effectively reduce the training…

Computation and Language · Computer Science 2023-05-25 Qihuang Zhong , Liang Ding , Juhua Liu , Xuebo Liu , Min Zhang , Bo Du , Dacheng Tao