English
Related papers

Related papers: Universal Transformers Need Memory: Depth-State Tr…

200 papers

Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…

Computation and Language · Computer Science 2025-11-20 Xiuying Wei , Anunay Yadav , Razvan Pascanu , Caglar Gulcehre

Conditional computation is a popular strategy to make Transformers more efficient. Existing methods often target individual modules (e.g., mixture-of-experts layers) or skip layers independently of one another. However, interpretability…

Machine Learning · Computer Science 2025-06-27 Tim Lawson , Laurence Aitchison

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Computation and Language · Computer Science 2021-09-13 Hongfei Xu , Qiuhui Liu , Josef van Genabith , Deyi Xiong

Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…

Computation and Language · Computer Science 2021-02-17 Mikhail S. Burtsev , Yuri Kuratov , Anton Peganov , Grigory V. Sapunov

Training large neural network (NN) models requires extensive memory resources, and Activation Compressed Training (ACT) is a promising approach to reduce training memory footprint. This paper presents GACT, an ACT framework to support a…

Test-time compute is emerging as a new paradigm for enhancing language models' complex multi-step reasoning capabilities, as demonstrated by the success of OpenAI's o1 and o3, as well as DeepSeek's R1. Compared to explicit reasoning in…

Computation and Language · Computer Science 2025-06-03 Tianhe Lin , Jian Xie , Siyu Yuan , Deqing Yang

Transformers have demonstrated strong performance across a wide range of sequence modeling tasks, but their quadratic attention complexity limits scalability to long sequences. Linear models such as Mamba and sliding-window attention (SWA)…

Machine Learning · Computer Science 2025-09-03 Aref Jafari , Yuhe Fan , Benyamin Jamialahmadi , Parsa Farinneya , Boxing Chen , Marzieh S. Tahaei

The Transformer architecture has shown to be a powerful tool for a wide range of tasks. It is based on the self-attention mechanism, which is an inherently computationally expensive operation with quadratic computational complexity: memory…

Machine Learning · Computer Science 2024-02-07 Adjorn van Engelenhoven , Nicola Strisciuglio , Estefanía Talavera

Emerging from the pairwise attention in conventional Transformers, there is a growing interest in sparse attention mechanisms that align more closely with localized, contextual learning in the biological brain. Existing studies such as the…

Machine Learning · Computer Science 2025-03-12 Yuwei Sun , Hideya Ochiai , Zhirong Wu , Stephen Lin , Ryota Kanai

The ability to reason lies at the core of artificial intelligence (AI), and challenging problems usually call for deeper and longer reasoning to tackle. A crucial question about AI reasoning is whether models can extrapolate learned…

Machine Learning · Computer Science 2025-11-11 Yu Huang , Zixin Wen , Aarti Singh , Yuejie Chi , Yuxin Chen

Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent…

Machine Learning · Computer Science 2026-03-24 Hung-Hsuan Chen

Transformers usually expose one inference cost per trained model, while deployed systems often need multiple cost-quality operating points. We study Budgeted Attention Allocation, a monotone head-gating mechanism conditioned on a requested…

Machine Learning · Computer Science 2026-05-08 Amrit Nidhi

Standard masked discrete diffusion models face limitations in reasoning tasks due to their inability to correct their own mistakes on the masking path. Since they rely on a fixed number of denoising steps, they are unable to adjust their…

Machine Learning · Computer Science 2026-03-26 Gregor Kornhardt , Jannis Chemseddine , Christian Wald , Gabriele Steidl

Deep learning has achieved remarkable success in modeling sequential data, including event sequences, temporal point processes, and irregular time series. Recently, transformers have largely replaced recurrent networks in these tasks.…

Machine Learning · Computer Science 2025-08-05 Ivan Karpukhin , Andrey Savchenko

Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource consumption, and a tendency…

Computation and Language · Computer Science 2025-08-05 Hang Yuan , Bin Yu , Haotian Li , Shijun Yang , Christina Dan Wang , Zhou Yu , Xueyin Xu , Weizhen Qi , Kai Chen

Depth-adaptive neural networks can dynamically adjust depths according to the hardness of input words, and thus improve efficiency. The main challenge is how to measure such hardness and decide the required depths (i.e., layers) to conduct.…

Computation and Language · Computer Science 2020-12-17 Yijin Liu , Fandong Meng , Jie Zhou , Yufeng Chen , Jinan Xu

Learning and memory are intertwined in our brain and their relationship is at the core of several recent neural network models. In particular, the Attention-Gated MEmory Tagging model (AuGMEnT) is a reinforcement learning network with an…

Neurons and Cognition · Quantitative Biology 2019-02-19 Marco Martinolli , Wulfram Gerstner , Aditya Gilra

In this paper, I introduce the retrieval problem, a simple yet common reasoning task that can be solved only by transformers with a minimum number of layers, which grows logarithmically with the input size. I empirically show that large…

Machine Learning · Computer Science 2025-10-29 Tiberiu Musat

This study explores the learnability of memory-less and memory-augmented RNNs, which are theoretically equivalent to Pushdown Automata. Empirical results show that these models often fail to generalize on longer sequences, relying more on…

Computation and Language · Computer Science 2024-10-07 Shrabon Das , Ankur Mali

This work introduces a novel Retention Layer mechanism for Transformer based architectures, addressing their inherent lack of intrinsic retention capabilities. Unlike human cognition, which can encode and dynamically recall symbolic…

Machine Learning · Computer Science 2025-01-17 M. Murat Yaslioglu
‹ Prev 1 4 5 6 7 8 10 Next ›