相关论文: Evidential Sparsification of Multimodal Latent Spa…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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)…
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…
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…
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…
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…
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…
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…
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…