中文
相关论文

相关论文: Evidential Sparsification of Multimodal Latent Spa…

200 篇论文

We propose a novel approach to train a multi-modal policy from mixed demonstrations without their behavior labels. We develop a method to discover the latent factors of variation in the demonstrations. Specifically, our method is based on…

机器学习 · 计算机科学 2019-03-26 Fang-I Hsiao , Jui-Hsuan Kuo , Min Sun

While sparse autoencoders (SAEs) successfully extract interpretable features from language models, applying them to audio generation faces unique challenges: audio's dense nature requires compression that obscures semantic meaning, and…

机器学习 · 计算机科学 2025-10-31 Nathan Paek , Yongyi Zang , Qihui Yang , Randal Leistikow

High annotation costs are a major bottleneck for the training of semantic segmentation systems. Therefore, methods working with less annotation effort are of special interest. This paper studies the problem of semi-supervised semantic…

计算机视觉与模式识别 · 计算机科学 2021-03-22 Olga Zatsarynna , Johann Sawatzky , Juergen Gall

Discovering the partial differential equations underlying spatio-temporal datasets from very limited and highly noisy observations is of paramount interest in many scientific fields. However, it remains an open question to know when model…

机器学习 · 统计学 2021-10-06 Georges Tod , Gert-Jan Both , Remy Kusters

We study video-specific autoencoders that allow a human user to explore, edit, and efficiently transmit videos. Prior work has independently looked at these problems (and sub-problems) and proposed different formulations. In this work, we…

计算机视觉与模式识别 · 计算机科学 2022-01-11 Kevin Wang , Deva Ramanan , Aayush Bansal

We develop data-driven methods for incorporating physical information for priors to learn parsimonious representations of nonlinear systems arising from parameterized PDEs and mechanics. Our approach is based on Variational Autoencoders…

机器学习 · 计算机科学 2021-03-17 Ryan Lopez , Paul J. Atzberger

Unsupervised learning with functional data is an emerging paradigm of machine learning research with applications to computer vision, climate modeling and physical systems. A natural way of modeling functional data is by learning operators…

机器学习 · 计算机科学 2023-02-22 Jacob H. Seidman , Georgios Kissas , George J. Pappas , Paris Perdikaris

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the…

计算与语言 · 计算机科学 2024-02-14 Xinyi Wang , Wanrong Zhu , Michael Saxon , Mark Steyvers , William Yang Wang

Causal representation learning has emerged as the center of action in causal machine learning research. In particular, multi-domain datasets present a natural opportunity for showcasing the advantages of causal representation learning over…

机器学习 · 计算机科学 2023-12-12 Kartik Ahuja , Amin Mansouri , Yixin Wang

Machine learning has made important headway in helping to improve the treatment of quantum many-body systems. A domain of particular relevance are correlated inhomogeneous systems. What has been missing so far is a general, scalable…

量子物理 · 物理学 2026-02-10 Alex Blania , Sandro Herbig , Fabian Dechent , Evert van Nieuwenburg , Florian Marquardt

Robots rely on visual relocalization to estimate their pose from camera images when they lose track. One of the challenges in visual relocalization is repetitive structures in the operation environment of the robot. This calls for…

计算机视觉与模式识别 · 计算机科学 2024-10-08 Fereidoon Zangeneh , Leonard Bruns , Amit Dekel , Alessandro Pieropan , Patric Jensfelt

We present a representation learning framework for financial time series forecasting. One challenge of using deep learning models for finance forecasting is the shortage of available training data when using small datasets. Direct trend…

机器学习 · 计算机科学 2021-05-10 Hanwei Wu , Ather Gattami , Markus Flierl

Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…

计算与语言 · 计算机科学 2025-02-04 Daniel Pluth , Yu Zhou , Vijay K. Gurbani

In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex…

机器学习 · 计算机科学 2023-11-10 Anshuk Uppal , Kristoffer Stensbo-Smidt , Wouter Boomsma , Jes Frellsen

Neural solvers for partial differential equations (PDEs) have great potential to generate fast and accurate physics solutions, yet their practicality is currently limited by their generalizability. PDEs evolve over broad scales and exhibit…

机器学习 · 计算机科学 2024-12-06 Anthony Zhou , Amir Barati Farimani

Recent advances in deep learning have shown their ability to learn strong feature representations for images. The task of image clustering naturally requires good feature representations to capture the distribution of the data and…

计算机视觉与模式识别 · 计算机科学 2020-05-12 Vignesh Prasad , Dipanjan Das , Brojeshwar Bhowmick

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Samuel Stevens , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su

Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical…

计算机视觉与模式识别 · 计算机科学 2021-10-28 Francesco Barbato , Umberto Michieli , Marco Toldo , Pietro Zanuttigh

This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world. We introduce…

机器学习 · 统计学 2017-10-31 Marco Fraccaro , Simon Kamronn , Ulrich Paquet , Ole Winther

Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised…

计算机视觉与模式识别 · 计算机科学 2021-06-11 Alexander H. Liu , SouYoung Jin , Cheng-I Jeff Lai , Andrew Rouditchenko , Aude Oliva , James Glass