English
Related papers

Related papers: Modes of Sequence Models and Learning Coefficients

200 papers

Transfer learning enhances model performance by utilizing knowledge from related domains, particularly when labeled data is scarce. While existing research addresses transfer learning under various distribution shifts in independent…

Machine Learning · Computer Science 2025-04-30 Liyuan Wang , Jiachen Chen , Kathryn L. Lunetta , Danyang Huang , Huimin Cheng , Debarghya Mukherjee

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Computation and Language · Computer Science 2026-01-22 Baturay Saglam , Paul Kassianik , Blaine Nelson , Sajana Weerawardhena , Yaron Singer , Amin Karbasi

We propose a discrete latent distribution for Generative Adversarial Networks (GANs). Instead of drawing latent vectors from a continuous prior, we sample from a finite set of learnable latents. However, a direct parametrization of such a…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Evangelos Ntavelis , Mohamad Shahbazi , Iason Kastanis , Radu Timofte , Martin Danelljan , Luc Van Gool

Sequence-to-sequence learning with neural networks has become the de facto standard for sequence prediction tasks. This approach typically models the local distribution over the next word with a powerful neural network that can condition on…

Computation and Language · Computer Science 2021-11-17 Yoon Kim

Transformers have demonstrated remarkable in-context learning (ICL) capabilities. The strong ICL performance of transformers is commonly believed to arise from their ability to implicitly execute certain algorithms on the context, thereby…

Machine Learning · Computer Science 2026-05-08 Chenyang Zhang , Yuan Cao

We propose a novel approach for preserving topological structures of the input space in latent representations of autoencoders. Using persistent homology, a technique from topological data analysis, we calculate topological signatures of…

Machine Learning · Computer Science 2021-06-01 Michael Moor , Max Horn , Bastian Rieck , Karsten Borgwardt

Statistical inference from high-dimensional data with low-dimensional structures has recently attracted lots of attention. In machine learning, deep generative modeling approaches implicitly estimate distributions of complex objects by…

Statistics Theory · Mathematics 2022-02-21 Rong Tang , Yun Yang

We present a new latent model of natural images that can be learned on large-scale datasets. The learning process provides a latent embedding for every image in the training dataset, as well as a deep convolutional network that maps the…

Computer Vision and Pattern Recognition · Computer Science 2018-11-06 ShahRukh Athar , Evgeny Burnaev , Victor Lempitsky

Despite the remarkable practical success of transformer-based language models, recent work has raised concerns about their ability to perform state tracking. In particular, a growing body of literature has shown this limitation primarily…

Machine Learning · Computer Science 2026-02-23 M. Reza Ebrahimi , Michaël Defferrard , Sunny Panchal , Roland Memisevic

Sampling-based methods have become a cornerstone of contemporary approaches to Model Predictive Control (MPC), as they make no restrictions on the differentiability of the dynamics or cost function and are straightforward to parallelize.…

Robotics · Computer Science 2022-12-07 Jacob Sacks , Byron Boots

When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-sequence modeling we are interested in high-quality translated…

Machine Learning · Computer Science 2020-10-05 Xi Gao , Han Zhang , Aliakbar Panahi , Tom Arodz

This work studies the entity-wise topical behavior from massive network logs. Both the temporal and the spatial relationships of the behavior are explored with the learning architectures combing the recurrent neural network (RNN) and the…

Machine Learning · Computer Science 2017-05-04 Shih-Chieh Su

LiDAR relocalization has attracted increasing attention as it can deliver accurate 6-DoF pose estimation in complex 3D environments. Recent learning-based regression methods offer efficient solutions by directly predicting global poses…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Jianshi Wu , Minghang Zhu , Dunqiang Liu , Wen Li , Sheng Ao , Siqi Shen , Chenglu Wen , Cheng Wang

Transformers have revolutionized machine learning and deploying attention layers in the model is increasingly standard across a myriad of applications. Further, for large models, it is common to implement Low Rank Adaptation (LoRA), whereby…

Machine Learning · Computer Science 2026-05-11 Zhengkai Sun , Dibyakanti Kumar , Alejandro F Frangi , Anirbit Mukherjee , Mingfei Sun

In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We…

Computer Vision and Pattern Recognition · Computer Science 2020-09-02 Shuyu Lin , Ronald Clark

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

Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive…

Machine Learning · Computer Science 2025-06-03 Yifan Hao , Chenlu Ye , Chi Han , Tong Zhang

We consider the problem of parameter estimation using weakly supervised datasets, where a training sample consists of the input and a partially specified annotation, which we refer to as the output. The missing information in the annotation…

Machine Learning · Computer Science 2012-06-22 M. Pawan Kumar , Ben Packer , Daphne Koller

Transformers have demonstrated remarkable in-context learning (ICL) capabilities, adapting to new tasks by simply conditioning on demonstrations without parameter updates. Compelling empirical and theoretical evidence suggests that ICL, as…

Machine Learning · Computer Science 2025-10-28 Taejong Joo , Diego Klabjan

Despite the non-convex optimization landscape, over-parametrized shallow networks are able to achieve global convergence under gradient descent. The picture can be radically different for narrow networks, which tend to get stuck in…

Machine Learning · Statistics 2023-06-16 Rodrigo Veiga , Ludovic Stephan , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová