Zobrazeno 1 - 10
of 158
pro vyhledávání: '"Ilin, Alexander"'
Publikováno v:
IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 2024
This paper explores the efficacy of diffusion-based generative models as neural operators for partial differential equations (PDEs). Neural operators are neural networks that learn a mapping from the parameter space to the solution space of PDEs from
Externí odkaz:
http://arxiv.org/abs/2405.07097
Deep learning is providing a wealth of new approaches to the old problem of novel view synthesis, from Neural Radiance Field (NeRF) based approaches to end-to-end style architectures. Each approach offers specific strengths but also comes with specif
Externí odkaz:
http://arxiv.org/abs/2402.02906
Solving complex planning problems has been a long-standing challenge in computer science. Learning-based subgoal search methods have shown promise in tackling these problems, but they often suffer from a lack of completeness guarantees, meaning that
Externí odkaz:
http://arxiv.org/abs/2310.12819
Developing reliable autonomous driving algorithms poses challenges in testing, particularly when it comes to safety-critical traffic scenarios involving pedestrians. An open question is how to simulate rare events, not necessarily found in autonomous
Externí odkaz:
http://arxiv.org/abs/2309.00249
Autor:
Heimann, Nicolas, Broers, Lukas, Pintul, Nejira, Petersen, Tobias, Sponselee, Koen, Ilin, Alexander, Becker, Christoph, Mathey, Ludwig
We demonstrate machine learning assisted design of a two-qubit gate in a Rydberg tweezer system. Two low-energy hyperfine states in each of the atoms represent the logical qubit and a Rydberg state acts as an auxiliary state to induce qubit interacti
Externí odkaz:
http://arxiv.org/abs/2306.08691
Meta-learning and few-shot prompting are viable methods to induce certain types of compositional behaviour. However, these methods can be very sensitive to the choice of support examples used. Choosing good supports from the training data for a given
Externí odkaz:
http://arxiv.org/abs/2305.13092
The ability to plan actions on multiple levels of abstraction enables intelligent agents to solve complex tasks effectively. However, learning the models for both low and high-level planning from demonstrations has proven challenging, especially with
Externí odkaz:
http://arxiv.org/abs/2301.12962
Autor:
Vikström, Oscar, Ilin, Alexander
With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features expressiv
Externí odkaz:
http://arxiv.org/abs/2210.14139
Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the quality of the offline dataset, such pre-trained agents may have limited
Externí odkaz:
http://arxiv.org/abs/2210.13846
Online planning is crucial for high performance in many complex sequential decision-making tasks. Monte Carlo Tree Search (MCTS) employs a principled mechanism for trading off exploration for exploitation for efficient online planning, and it outperf
Externí odkaz:
http://arxiv.org/abs/2210.01426