Zobrazeno 1 - 10
of 12 304
pro vyhledávání: '"P Kale"'
Autor:
Kapoor, Aditya, Swamy, Sushant, Tessera, Kale-ab, Baranwal, Mayank, Sun, Mingfei, Khadilkar, Harshad, Albrecht, Stefano V.
In multi-agent environments, agents often struggle to learn optimal policies due to sparse or delayed global rewards, particularly in long-horizon tasks where it is challenging to evaluate actions at intermediate time steps. We introduce Temporal-Age
Externí odkaz:
http://arxiv.org/abs/2412.14779
We tackle the challenge of open-vocabulary segmentation, where we need to identify objects from a wide range of categories in different environments, using text prompts as our input. To overcome this challenge, existing methods often use multi-modal
Externí odkaz:
http://arxiv.org/abs/2412.10292
Balancing individual specialisation and shared behaviours is a critical challenge in multi-agent reinforcement learning (MARL). Existing methods typically focus on encouraging diversity or leveraging shared representations. Full parameter sharing (Fu
Externí odkaz:
http://arxiv.org/abs/2412.04233
Parallel input performance issues are often neglected in large scale parallel applications in Computational Science and Engineering. Traditionally, there has been less focus on input performance because either input sizes are small (as in biomolecula
Externí odkaz:
http://arxiv.org/abs/2411.18593
This paper explores the application of a reinforcement learning (RL) framework using the Q-Learning algorithm to enhance dynamic pricing strategies in the retail sector. Unlike traditional pricing methods, which often rely on static demand models, ou
Externí odkaz:
http://arxiv.org/abs/2411.18261
Autor:
Deng, Shijian, Zhao, Wentian, Li, Yu-Jhe, Wan, Kun, Miranda, Daniel, Kale, Ajinkya, Tian, Yapeng
Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and potential pitfa
Externí odkaz:
http://arxiv.org/abs/2411.17760
Diffuse radio sources known as radio relics are direct tracers of shocks in the outskirts of merging galaxy clusters. PSZ2 G200.95-28.16, a low-mass merging cluster($\textrm{M}_{500} = (2.7 \pm 0.2) \times 10^{14}~\mathrm{M}_{\odot}$) features a prom
Externí odkaz:
http://arxiv.org/abs/2411.15480
Learning high-dimensional distributions is a significant challenge in machine learning and statistics. Classical research has mostly concentrated on asymptotic analysis of such data under suitable assumptions. While existing works [Bhattacharyya et a
Externí odkaz:
http://arxiv.org/abs/2411.11516
This paper presents a novel method for discovering systematic errors in segmentation models. For instance, a systematic error in the segmentation model can be a sufficiently large number of misclassifications from the model as a parking meter for a t
Externí odkaz:
http://arxiv.org/abs/2411.10845
Autor:
Chandrasekar, Kavitha, Kale, Laxmikant
Message aggregation is often used with a goal to reduce communication cost in HPC applications. The difference in the order of overhead of sending a message and cost of per byte transferred motivates the need for message aggregation, for several irre
Externí odkaz:
http://arxiv.org/abs/2411.03533