Related papers: FAIR: Flow Type-Aware Pre-Training of Compiler Int…
We tackle the problem of estimating flow between two images with large lighting variations. Recent learning-based flow estimation frameworks have shown remarkable performance on image pairs with small displacement and constant…
We study a practical setting of continual learning: fine-tuning on a pre-trained model continually. Previous work has found that, when training on new tasks, the features (penultimate layer representations) of previous data will change,…
Given everyday artifacts, such as tables and chairs, humans recognize high-level regularities within them, such as the symmetries of a table, the repetition of its legs, while possessing low-level priors of their geometries, e.g., surfaces…
Variational inference often struggles with the posterior geometry exhibited by complex hierarchical Bayesian models. Recent advances in flow-based variational families and Variationally Inferred Parameters (VIP) each address aspects of this…
Post-training of flow matching models-aligning the output distribution with a high-quality target-is mathematically equivalent to imitation learning. While Supervised Fine-Tuning mimics expert demonstrations effectively, it cannot correct…
Floods can cause horrific harm to life and property. However, they can be mitigated or even avoided by the effective use of hydraulic structures such as dams, gates, and pumps. By pre-releasing water via these structures in advance of…
This paper presents a software-based technique to recover control-flow errors in multithreaded programs. Control-flow error recovery is achieved through inserting additional instructions into multithreaded program at compile time regarding…
In this paper, we investigate the problem of automatically controllable artistic character line drawing generation from photographs by proposing a Vector Flow Aware and Line Controllable Image-to-Image Translation architecture, which can be…
Source code spends most of its time in a broken or incomplete state during software development. This presents a challenge to machine learning for code, since high-performing models typically rely on graph structured representations of…
Two fundamental problems in unsupervised learning are efficient inference for latent-variable models and robust density estimation based on large amounts of unlabeled data. Algorithms for the two tasks, such as normalizing flows and…
Combinatorial optimization problems are ubiquitous in science and engineering. Still, learning-based approaches to accelerate combinatorial optimization often require solving a large number of difficult instances to collect training data,…
This paper proposes a step toward obtaining general models of knowledge for facial analysis, by addressing the question of multi-source transfer learning. More precisely, the proposed approach consists in two successive training steps: the…
Incompressible fluid flow around a cylinder is one of the classical problems in fluid-dynamics with strong relevance with many real-world engineering problems, for example, design of offshore structures or design of a pin-fin heat…
Despite constant improvements in efficiency, today's data centers and networks consume enormous amounts of energy and this demand is expected to rise even further. An important research question is whether and how fog computing can curb…
Cross-device federated learning is an emerging machine learning (ML) paradigm where a large population of devices collectively train an ML model while the data remains on the devices. This research field has a unique set of practical…
Normalizing flows are a powerful class of generative models demonstrating strong performance in several speech and vision problems. In contrast to other generative models, normalizing flows are latent variable models with tractable…
In recent years, there have been numerous developments towards solving multimodal tasks, aiming to learn a stronger representation than through a single modality. Certain aspects of the data can be particularly useful in this case - for…
In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel…
Learning to compute, the ability to model the functional behavior of a circuit graph, is a fundamental challenge for graph representation learning. Yet, the dominant paradigm is architecturally mismatched for this task. This flawed…
While visuomotor policy has made advancements in recent years, contact-rich tasks still remain a challenge. Robotic manipulation tasks that require continuous contact demand explicit handling of compliance and force. However, most…