English
Related papers

Related papers: Scaling Algorithm Distillation for Continuous Cont…

200 papers

We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill), a new method that enables reinforcement learning (RL) to perform long-horizon robot control problems by distilling behaviors from auxiliary RL tasks. AuxDistill…

Machine Learning · Computer Science 2024-06-26 Abhinav Narayan Harish , Larry Heck , Josiah P. Hanna , Zsolt Kira , Andrew Szot

Pre-trained transformer models with extended context windows are notoriously expensive to run at scale, often limiting real-world deployment due to their high computational and memory requirements. In this paper, we introduce Hamming…

Machine Learning · Computer Science 2025-02-05 Mark Horton , Tergel Molom-Ochir , Peter Liu , Bhavna Gopal , Chiyue Wei , Cong Guo , Brady Taylor , Deliang Fan , Shan X. Wang , Hai Li , Yiran Chen

State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL), a variant of meta-learning concerning the learned ability to solve tasks during a neural network forward pass, exploiting contextual…

Machine Learning · Computer Science 2024-04-25 Riccardo Grazzi , Julien Siems , Simon Schrodi , Thomas Brox , Frank Hutter

Adversarial attacks pose a significant threat to the security and safety of deep neural networks being applied to modern applications. More specifically, in computer vision-based tasks, experts can use the knowledge of model architecture to…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Maniratnam Mandal , Suna Gao

Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have limitations in offline RL settings. In this study, we explore the integration of RL…

In-context learning allows models like transformers to adapt to new tasks from a few examples without updating their weights, a desirable trait for reinforcement learning (RL). However, existing in-context RL methods, such as Algorithm…

The current era of Natural Language Processing (NLP) is dominated by Transformer models. However, novel architectures relying on recurrent mechanisms, such as xLSTM and Mamba, have been proposed as alternatives to attention-based models.…

Machine Learning · Computer Science 2025-03-25 Abdoul Majid O. Thiombiano , Brahim Hnich , Ali Ben Mrad , Mohamed Wiem Mkaouer

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Zelong Zeng , Fan Yang , Zheng Wang , Shin'ichi Satoh

Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical…

Machine Learning · Computer Science 2026-02-04 Mahyar Alinejad , Yue Wang , George Atia

Sequential Recommenders have been widely applied in various online services, aiming to model users' dynamic interests from their sequential interactions. With users increasingly engaging with online platforms, vast amounts of lifelong user…

Information Retrieval · Computer Science 2024-03-26 Jiyuan Yang , Yuanzi Li , Jingyu Zhao , Hanbing Wang , Muyang Ma , Jun Ma , Zhaochun Ren , Mengqi Zhang , Xin Xin , Zhumin Chen , Pengjie Ren

Extractive summarization of long documents is bottlenecked by quadratic complexity, often forcing truncation and limiting deployment in resource-constrained settings. We introduce the first Mamba-Transformer hybrid for extractive…

Computation and Language · Computer Science 2026-03-03 Nisrine Ait Khayi

State space models (SSMs) for language modelling promise an efficient and performant alternative to quadratic-attention Transformers, yet show variable performance on recalling basic information from the context. While performance on…

Computation and Language · Computer Science 2026-02-02 Aryaman Arora , Neil Rathi , Nikil Roashan Selvam , Róbert Csordás , Dan Jurafsky , Christopher Potts

Deep Metric Learning (DML) provides a crucial tool for visual similarity and zero-shot applications by learning generalizing embedding spaces, although recent work in DML has shown strong performance saturation across training objectives.…

Computer Vision and Pattern Recognition · Computer Science 2021-06-08 Karsten Roth , Timo Milbich , Björn Ommer , Joseph Paul Cohen , Marzyeh Ghassemi

We introduce a novel approach to large language model (LLM) distillation by formulating it as a constrained reinforcement learning problem. While recent work has begun exploring the integration of task-specific rewards into distillation…

Machine Learning · Computer Science 2025-09-30 Matthieu Zimmer , Xiaotong Ji , Tu Nguyen , Haitham Bou Ammar

Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical…

Computation and Language · Computer Science 2025-09-03 Weihua Du , Pranjal Aggarwal , Sean Welleck , Yiming Yang

Dataset Distillation is a newly emerging area that aims to distill large datasets into much smaller and highly informative synthetic ones to accelerate training and reduce storage. Among various dataset distillation methods,…

Computer Vision and Pattern Recognition · Computer Science 2023-11-02 Justin Cui , Ruochen Wang , Si Si , Cho-Jui Hsieh

Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL). Yet, it poses challenges due to substantial parameter size and limited scalability, which is…

Machine Learning · Computer Science 2024-10-29 Yang Dai , Oubo Ma , Longfei Zhang , Xingxing Liang , Shengchao Hu , Mengzhu Wang , Shouling Ji , Jincai Huang , Li Shen

Data augmentation have been intensively used in training deep neural network to improve the generalization, whether in original space (e.g., image space) or representation space. Although being successful, the connection between the…

Machine Learning · Computer Science 2020-06-30 Qian Li , Qingyuan Hu , Yong Qi , Saiyu Qi , Jie Ma , Jian Zhang

The Mamba model has gained significant attention for its computational advantages over Transformer-based models, while achieving comparable performance across a wide range of language tasks. Like Transformers, Mamba exhibits in-context…

Machine Learning · Computer Science 2025-10-02 Hongkang Li , Songtao Lu , Xiaodong Cui , Pin-Yu Chen , Meng Wang

In this paper, we explore multi-task learning (MTL) as a second pretraining step to learn enhanced universal language representation for transformer language models. We use the MTL enhanced representation across several natural language…

Computation and Language · Computer Science 2021-03-17 Haytham ElFadeel , Stan Peshterliev