English
Related papers

Related papers: Training-Free Looped Transformers

200 papers

We reformulate the problem of supervised learning as learning to learn with two nested loops (i.e. learning problems). The inner loop learns on each individual instance with self-supervision before final prediction. The outer loop learns…

Machine Learning · Computer Science 2024-01-09 Yu Sun , Xinhao Li , Karan Dalal , Chloe Hsu , Sanmi Koyejo , Carlos Guestrin , Xiaolong Wang , Tatsunori Hashimoto , Xinlei Chen

LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it couples task adaptation to full-depth activation storage, long-range backward…

Computation and Language · Computer Science 2026-05-11 Hengyu Shi , Tianyang Han , Peizhe Wang , Zhiling Wang , Xu Yang , Junhao Su

In this paper, we explore a strategy that uses Mixture-of-Experts (MoE) to streamline, rather than augment, vision transformers. Each expert in an MoE layer is a SwiGLU feedforward network, where V and W2 are shared across the layer. No…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Jen Hong Tan

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hemanth Saratchandran , Simon Lucey

Deep learning models have been widely applied in various aspects of daily life. Many variant models based on deep learning structures have achieved even better performances. Attention-based architectures have become almost ubiquitous in…

Machine Learning · Computer Science 2022-02-25 Zhiying Fang , Yidong Ouyang , Ding-Xuan Zhou , Guang Cheng

Meta-learning optimizes the hyperparameters of a training procedure, such as its initialization, kernel, or learning rate, based on data sampled from a number of auxiliary tasks. A key underlying assumption is that the auxiliary tasks,…

Machine Learning · Computer Science 2021-11-10 Yunchuan Zhang , Sharu Theresa Jose , Osvaldo Simeone

Large Language Models (LLMs) have demonstrated remarkable efficacy in text embedding, yet current adaptation methods like LoRA face significant bottlenecks in computational efficiency and cross-architecture transferability. Whenever a new…

Computation and Language · Computer Science 2026-05-28 Yu-Che Tsai , Kuan-Yu Chen , Yuan-Hao Chen , Yu-Han Chang , Ching-Yu Tsai , Yu-Hsiang Chuang , Shou-De Lin

State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' parameter counts and computational costs without significantly…

Computation and Language · Computer Science 2024-11-07 Xiuying Wei , Skander Moalla , Razvan Pascanu , Caglar Gulcehre

While scaling Transformer-based large language models (LLMs) has demonstrated promising performance across various tasks, it also introduces redundant architectures, posing efficiency challenges for real-world deployment. Despite some…

Machine Learning · Computer Science 2024-10-18 Shwai He , Guoheng Sun , Zheyu Shen , Ang Li

Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including most recently language modeling and reasoning. To demystify…

Machine Learning · Computer Science 2026-02-24 Halil Alperen Gozeten , M. Emrullah Ildiz , Xuechen Zhang , Mahdi Soltanolkotabi , Marco Mondelli , Samet Oymak

State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forgetting. However, there is a tradeoff between the number of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Thomas De Min , Massimiliano Mancini , Karteek Alahari , Xavier Alameda-Pineda , Elisa Ricci

Continual learning in transformers is commonly addressed through parameter-efficient adaptation: prompts, adapters, or LoRA modules are specialized per task while the backbone remains frozen. Although effective in controlled multi-epoch…

Machine Learning · Computer Science 2026-03-11 Alessio Masano , Giovanni Bellitto , Dipam Goswani , Joost Van de Weijer , Concetto Spampinato

At typical context lengths, the feed-forward MLP block accounts for a large share of a transformer's compute budget, motivating sparse alternatives to dense MLP blocks. We study sparse, tree-structured feed-forward layers as drop-in…

Computation and Language · Computer Science 2026-04-13 Reza Sedghi , Robin Schiewer , Anand Subramoney , David Kappel

Looped Transformers provide advantages in parameter efficiency, computational capabilities, and generalization for reasoning tasks. However, their expressive power regarding function approximation remains underexplored. In this paper, we…

Machine Learning · Computer Science 2025-06-06 Kevin Xu , Issei Sato

In many practical control applications, the performance level of a closed-loop system degrades over time due to the change of plant characteristics. Thus, there is a strong need for redesigning a controller without going through the system…

Systems and Control · Electrical Eng. & Systems 2023-12-01 Mei Minami , Yuka Masumoto , Yoshihiro Okawa , Tomotake Sasaki , Yutaka Hori

Model-free Reinforcement Learning (RL) algorithms such as Q-learning [Watkins, Dayan 92] have been widely used in practice and can achieve human level performance in applications such as video games [Mnih et al. 15]. Recently, equipped with…

Machine Learning · Computer Science 2019-05-03 Zhao Song , Wen Sun

Loops--short audio segments designed for seamless repetition--are central to many music genres, particularly those rooted in dance and electronic styles. However, current generative music models struggle to produce truly loopable audio, as…

In this paper, we study trade-offs between efficiency, cost and accuracy when pre-training Transformer encoders with different pre-training objectives. For this purpose, we analyze features of common objectives and combine them to create…

Computation and Language · Computer Science 2022-10-26 Luca Di Liello , Matteo Gabburo , Alessandro Moschitti

Transformer-based models, exemplified by GPT-3, ChatGPT, and GPT-4, have recently garnered considerable attention in both academia and industry due to their promising performance in general language tasks. Nevertheless, these models…

Computation and Language · Computer Science 2023-09-19 Gaochen Dong , Wei Chen

We introduce the Block-Recurrent Transformer, which applies a transformer layer in a recurrent fashion along a sequence, and has linear complexity with respect to sequence length. Our recurrent cell operates on blocks of tokens rather than…

Machine Learning · Computer Science 2022-11-03 DeLesley Hutchins , Imanol Schlag , Yuhuai Wu , Ethan Dyer , Behnam Neyshabur
‹ Prev 1 3 4 5 6 7 10 Next ›