Zobrazeno 1 - 10
of 4 882
pro vyhledávání: '"Fekri, A."'
Autor:
Xu, Duo, Fekri, Faramarz
In real-world applications, the success of completing a task is often determined by multiple key steps which are distant in time steps and have to be achieved in a fixed time order. For example, the key steps listed on the cooking recipe should be ac
Externí odkaz:
http://arxiv.org/abs/2411.01425
Causal discovery in real-world systems, such as biological networks, is often complicated by feedback loops and incomplete data. Standard algorithms, which assume acyclic structures or fully observed data, struggle with these challenges. To address t
Externí odkaz:
http://arxiv.org/abs/2410.18918
Autor:
Xu, Duo, Fekri, Faramarz
In this study, we address the challenge of learning generalizable policies for compositional tasks defined by logical specifications. These tasks consist of multiple temporally extended sub-tasks. Due to the sub-task inter-dependencies and sparse rew
Externí odkaz:
http://arxiv.org/abs/2410.09686
Enhancing the reasoning capabilities of large language models (LLMs) remains a key challenge, especially for tasks that require complex, multi-step decision-making. Humans excel at these tasks by leveraging deliberate planning with an internal world
Externí odkaz:
http://arxiv.org/abs/2410.03136
In this paper, we address the problem of lossy semantic communication to reduce uncertainty about the State of the World (SotW) for deductive tasks in point to point communication. A key challenge is transmitting the maximum semantic information with
Externí odkaz:
http://arxiv.org/abs/2410.01676
One of the fundamental challenges in reinforcement learning (RL) is to take a complex task and be able to decompose it to subtasks that are simpler for the RL agent to learn. In this paper, we report on our work that would identify subtasks by using
Externí odkaz:
http://arxiv.org/abs/2410.01929
Recent advancements in large language models (LLMs) have significantly enhanced their capacity to aggregate and process information across multiple modalities, enabling them to perform a wide range of tasks such as multimodal data querying, tool usag
Externí odkaz:
http://arxiv.org/abs/2409.01495
Large Language Models (LLMs) have shown superior capability to solve reasoning problems with programs. While being a promising direction, most of such frameworks are trained and evaluated in settings with a prior knowledge of task requirements. Howev
Externí odkaz:
http://arxiv.org/abs/2406.13764
Autor:
Zhao, M., Taani, M., Cole, J., Crudele, B., Zou, B., Bhuiyan, N., Chowdhury, E., Duan, Y., Fekri, S., Harvey, D., Mitra, D., Raz, O., Thompson, A., Katori, T., Rakovich, A.
Publikováno v:
2024 JINST 19 P07014
Liquid scintillators are typically composed from organic compounds dissolved in organic solvents. However, usage of such material is often restricted due to fire safety and environmental reasons. Because of this, R\&D of water-based liquid scintillat
Externí odkaz:
http://arxiv.org/abs/2403.10122
Causal learning is a fundamental problem in statistics and science, offering insights into predicting the effects of unseen treatments on a system. Despite recent advances in this topic, most existing causal discovery algorithms operate under two key
Externí odkaz:
http://arxiv.org/abs/2402.15625