English
Related papers

Related papers: Training-Free Looped Transformers

200 papers

We propose Quick Feedforward (QF) Learning, a novel knowledge consolidation framework for transformer-based models that enables efficient transfer of instruction derived knowledge into model weights through feedforward activations without…

Machine Learning · Computer Science 2025-07-08 Feng Qi

Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by adjusting the activated experts in an input-dependent manner. Existing dynamic MoE methods…

We introduce the Autoregressive Block-Based Iterative Encoder (AbbIE), a novel recursive generalization of the encoder-only Transformer architecture, which achieves better perplexity than a standard Transformer and allows for the dynamic…

In search of a simple baseline for Deep Reinforcement Learning in locomotion tasks, we propose a model-free open-loop strategy. By leveraging prior knowledge and the elegance of simple oscillators to generate periodic joint motions, it…

Robotics · Computer Science 2024-03-05 Antonin Raffin , Olivier Sigaud , Jens Kober , Alin Albu-Schäffer , João Silvério , Freek Stulp

We propose a general model-free strategy for feedback control design of turbulent flows. This strategy called 'machine learning control' (MLC) is capable of exploiting nonlinear mechanisms in a systematic unsupervised manner. It relies on…

With the proliferation of mobile devices and the Internet of Things, deep learning models are increasingly deployed on devices with limited computing resources and memory, and are exposed to the threat of adversarial noise. Learning deep…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Xian Wei , Yanhui Huang , Yangyu Xu , Mingsong Chen , Hai Lan , Yuanxiang Li , Zhongfeng Wang , Xuan Tang

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…

Machine Learning · Computer Science 2026-05-26 Florent Draye , Anson Lei , Hsiao-Ru Pan , Ingmar Posner , Bernhard Schölkopf

Transient simulation of linear and nonlinear circuits remains an important task in modern EDA tools. At present, SPICE-like simulators face challenges in parallelization, nonlinear convergence and linear efficiency, especially when applied…

Computational Engineering, Finance, and Science · Computer Science 2025-11-21 Zijian Zhang , Yuanmiao Lin , Xuesong Chen , Shuting Cai

Transformers have demonstrated impressive in-context learning (ICL) capabilities, raising the question of whether they can serve as metalearners that adapt to new tasks using only a small number of in-context examples, without any further…

Machine Learning · Computer Science 2025-10-23 Roey Magen , Gal Vardi

We propose ways to improve the performance of fully connected networks. We found that two approaches in particular have a strong effect on performance: linear bottleneck layers and unsupervised pre-training using autoencoders without hidden…

Machine Learning · Computer Science 2015-11-10 Zhouhan Lin , Roland Memisevic , Kishore Konda

Transformers demonstrate significant advantages as the building block of modern LLMs. In this work, we study the capacities of Transformers in performing unsupervised learning. We show that multi-layered Transformers, given a sufficiently…

Machine Learning · Statistics 2025-01-14 Yihan He , Yuan Cao , Hong-Yu Chen , Dennis Wu , Jianqing Fan , Han Liu

Transformers excel empirically on tasks that process well-formed inputs according to some grammar, such as natural language and code. However, it remains unclear how they can process grammatical syntax. In fact, under standard complexity…

Machine Learning · Computer Science 2026-02-09 Selim Jerad , Anej Svete , Sophie Hao , Ryan Cotterell , William Merrill

Time series analysis is vital for numerous applications, and transformers have become increasingly prominent in this domain. Leading methods customize the transformer architecture from NLP and CV, utilizing a patching technique to convert…

Machine Learning · Computer Science 2024-02-09 Yanjun Zhao , Tian Zhou , Chao Chen , Liang Sun , Yi Qian , Rong Jin

As large language models (LLMs) become more prevalent, there is a growing need for new and improved quantization methods that can meet the computationalast layer demands of these modern architectures while maintaining the accuracy. In this…

Computation and Language · Computer Science 2023-10-18 Wenhua Cheng , Yiyang Cai , Kaokao Lv , Haihao Shen

Increasing the input length has been a driver of progress in language modeling with transformers. We identify conditions where shorter inputs are not harmful, and achieve perplexity and efficiency improvements through two new methods that…

Computation and Language · Computer Science 2021-06-04 Ofir Press , Noah A. Smith , Mike Lewis

Vision-language-action (VLA) models enable impressive zero shot manipulation, but their inference stacks are often too heavy for responsive web demos or high frequency robot control on commodity GPUs. We present BLURR, a lightweight…

Robotics · Computer Science 2025-12-15 Xiaoyu Ma , Zhengqing Yuan , Zheyuan Zhang , Kaiwen Shi , Lichao Sun , Yanfang Ye

Gradient-flow analyses show that simplified linear transformers can learn the in-context linear-regression algorithm, but they do not explain the finite-step behavior of gradient descent at large learning rates. Motivated by empirical work…

Machine Learning · Statistics 2026-05-21 Krishnakumar Balasubramanian

Efficient training and inference algorithms, such as low-rank adaption and model pruning, have shown impressive performance for learning Transformer-based large foundation models. However, due to the technical challenges of the non-convex…

Machine Learning · Computer Science 2024-06-26 Hongkang Li , Meng Wang , Shuai Zhang , Sijia Liu , Pin-Yu Chen

With the success of language pretraining, it is highly desirable to develop more efficient architectures of good scalability that can exploit the abundant unlabeled data at a lower cost. To improve the efficiency, we examine the…

Machine Learning · Computer Science 2020-06-08 Zihang Dai , Guokun Lai , Yiming Yang , Quoc V. Le

This paper presents a novel approach to learning free terminal time closed-loop control for robotic manipulation tasks, enabling dynamic adjustment of task duration and control inputs to enhance performance. We extend the supervised…

Optimization and Control · Mathematics 2025-07-15 Wei Hu , Yue Zhao , Weinan E , Jiequn Han , Jihao Long