English
Related papers

Related papers: When Attention Beats Fourier: Multi-Scale Transfor…

200 papers

Memory complexity and data scarcity have so far prohibited learning solution operators of partial differential equations (PDEs) at high resolutions. We address these limitations by introducing a new data efficient and highly parallelizable…

Machine Learning · Computer Science 2023-10-03 Jean Kossaifi , Nikola Kovachki , Kamyar Azizzadenesheli , Anima Anandkumar

Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with applications in a wide range of fields, from computer vision to natural language…

Computation and Language · Computer Science 2024-06-21 Martin Courtois , Malte Ostendorff , Leonhard Hennig , Georg Rehm

Neural operators, which aim to approximate mappings between infinite-dimensional function spaces, have been widely applied in the simulation and prediction of physical systems. However, the limited representational capacity of network…

Machine Learning · Computer Science 2025-06-03 Jin Song , Kenji Kawaguchi , Zhenya Yan

The fast simulation of dynamical systems is a key challenge in many scientific and engineering applications, such as weather forecasting, disease control, and drug discovery. With the recent success of deep learning, there is increasing…

Machine Learning · Computer Science 2024-10-02 Zezheng Song , Jiaxin Yuan , Haizhao Yang

Learning underlying dynamics from data is important and challenging in many real-world scenarios. Incorporating differential equations (DEs) to design continuous networks has drawn much attention recently, however, most prior works make…

Machine Learning · Computer Science 2023-02-03 Yesom Park , Jaemoo Choi , Changyeon Yoon , Chang hoon Song , Myungjoo Kang

Attention scores in transformers are bilinear forms $S_{ij} = x_i^\top M x_j / \sqrt{d_h}$ whose maximum magnitude governs overflow risk in low-precision training. We derive a \emph{rank-aware concentration inequality}: when the interaction…

Machine Learning · Computer Science 2026-02-24 Seyed Morteza Emadi

We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by…

Machine Learning · Statistics 2017-01-03 Oriol Vinyals , Meire Fortunato , Navdeep Jaitly

In solving partial differential equations (PDEs), Fourier Neural Operators (FNOs) have exhibited notable effectiveness. However, FNO is observed to be ineffective with large Fourier kernels that parameterize more frequencies. Current…

Machine Learning · Computer Science 2024-10-10 Shaoxiang Qin , Fuyuan Lyu , Wenhui Peng , Dingyang Geng , Ju Wang , Xing Tang , Sylvie Leroyer , Naiping Gao , Xue Liu , Liangzhu Leon Wang

Accurately modeling and forecasting complex systems governed by partial differential equations (PDEs) is crucial in various scientific and engineering domains. However, traditional numerical methods struggle in real-world scenarios due to…

Machine Learning · Computer Science 2025-05-06 Han Wan , Rui Zhang , Qi Wang , Yang Liu , Hao Sun

Structured dilated attention has an appealing inference-time efficiency knob: it reduces the FLOPs of attention and the KV cache size by a factor of the dilation size D, while preserving long-range connectivity. While prior work studies it…

Machine Learning · Computer Science 2026-05-29 Xiuying Wei , Caglar Gulcehre

Deep neural networks are typically trained in a single shot for a specific task and data distribution, but in real world settings both the task and the domain of application can change. The problem becomes even more challenging in dense…

Computer Vision and Pattern Recognition · Computer Science 2022-06-29 Donald Shenaj , Francesco Barbato , Umberto Michieli , Pietro Zanuttigh

The attention mechanism in its standard implementation contains extraneous rotational degrees of freedom that are carried through computation but do not affect model activations or outputs. We introduce a simple symmetry-breaking protocol…

Machine Learning · Computer Science 2026-02-13 Eva Silverstein , Daniel Kunin , Vasudev Shyam

Extending the context length of Language Models (LMs) by improving Rotary Position Embedding (RoPE) has become a trend. While prior works mainly address RoPE's limitations within attention, this paper uncovers the adverse effects on length…

Artificial Intelligence · Computer Science 2025-07-15 Ermo Hua , Che Jiang , Xingtai Lv , Kaiyan Zhang , Youbang Sun , Yuchen Fan , Xuekai Zhu , Biqing Qi , Ning Ding , Bowen Zhou

This paper presents AFD-STA Net, a neural framework integrating adaptive filtering and spatiotemporal dynamics learning for predicting high-dimensional chaotic systems governed by partial differential equations. The architecture combines:…

Machine Learning · Computer Science 2025-05-26 Chunlin Gong , Yin Wang , Jingru Li , Hanleran Zhang

Deep learning methods are emerging as popular computational tools for solving forward and inverse problems in traffic flow. In this paper, we study a neural operator framework for learning solutions to nonlinear hyperbolic partial…

Machine Learning · Computer Science 2024-06-26 Bilal Thonnam Thodi , Sai Venkata Ramana Ambadipudi , Saif Eddin Jabari

Pre-trained language models have been proven to possess strong base capabilities, which not only excel in in-distribution language modeling but also show powerful abilities in out-of-distribution language modeling, transfer learning and…

Computation and Language · Computer Science 2024-11-01 Xin Lu , Yanyan Zhao , Bing Qin , Liangyu Huo , Qing Yang , Dongliang Xu

Transformer networks have achieved remarkable success across diverse domains, leveraging a variety of architectural innovations, including residual connections. However, traditional residual connections, which simply sum the outputs of…

Machine Learning · Computer Science 2025-07-25 Mike Heddes , Adel Javanmard , Kyriakos Axiotis , Gang Fu , MohammadHossein Bateni , Vahab Mirrokni

In this work, we study how multi-head latent attention (MLA), a popular strategy for compressing key/value memory, affects a transformer's internal capacity during pretraining. Using a lightweight suite of Marchenko-Pastur (MP) diagnostics,…

Machine Learning · Computer Science 2025-07-15 Nandan Kumar Jha , Brandon Reagen

The advent of foundation models in AI has significantly advanced general-purpose learning, enabling remarkable capabilities in zero-shot inference and in-context learning. However, training such models on physics data, including solutions…

Machine Learning · Computer Science 2025-10-27 Hyunsu Kim , Jonggeon Park , Joan Bruna , Hongseok Yang , Juho Lee

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized…