Zobrazeno 1 - 10
of 6 754
pro vyhledávání: '"A. Mándi"'
Autor:
Chen, Zoey, Mandi, Zhao, Bharadhwaj, Homanga, Sharma, Mohit, Song, Shuran, Gupta, Abhishek, Kumar, Vikash
Generalization to unseen real-world scenarios for robot manipulation requires exposure to diverse datasets during training. However, collecting large real-world datasets is intractable due to high operational costs. For robot learning to generalize d
Externí odkaz:
http://arxiv.org/abs/2409.00951
Autor:
Mandi, Jayanta, Foschini, Marco, Holler, Daniel, Thiebaux, Sylvie, Hoffmann, Jorg, Guns, Tias
In many automated planning applications, action costs can be hard to specify. An example is the time needed to travel through a certain road segment, which depends on many factors, such as the current weather conditions. A natural way to address this
Externí odkaz:
http://arxiv.org/abs/2408.06876
We present Real2Code, a novel approach to reconstructing articulated objects via code generation. Given visual observations of an object, we first reconstruct its part geometry using an image segmentation model and a shape completion model. We then r
Externí odkaz:
http://arxiv.org/abs/2406.08474
Autor:
Xu, Nan, Rosander, Petter, Schäfer, Christian, Lindgren, Eric, Österbacka, Nicklas, Fang, Mandi, Chen, Wei, He, Yi, Fan, Zheyong, Erhart, Paul
Publikováno v:
Journal of Chemical Theory and Computation 20, 3273 (2024)
Infrared and Raman spectroscopy are widely used for the characterization of gases, liquids, and solids, as the spectra contain a wealth of information concerning in particular the dynamics of these systems. Atomic scale simulations can be used to pre
Externí odkaz:
http://arxiv.org/abs/2312.05233
Autor:
Duisterhof, Bardienus P., Mandi, Zhao, Yao, Yunchao, Liu, Jia-Wei, Seidenschwarz, Jenny, Shou, Mike Zheng, Ramanan, Deva, Song, Shuran, Birchfield, Stan, Wen, Bowen, Ichnowski, Jeffrey
Teaching robots to fold, drape, or reposition deformable objects such as cloth will unlock a variety of automation applications. While remarkable progress has been made for rigid object manipulation, manipulating deformable objects poses unique chall
Externí odkaz:
http://arxiv.org/abs/2312.00583
Visible-Infrared person re-identification (VI-ReID) is an important and challenging task in intelligent video surveillance. Existing methods mainly focus on learning a shared feature space to reduce the modality discrepancy between visible and infrar
Externí odkaz:
http://arxiv.org/abs/2308.15063
Autor:
Mandi, Jayanta, Kotary, James, Berden, Senne, Mulamba, Maxime, Bucarey, Victor, Guns, Tias, Fioretto, Ferdinando
Publikováno v:
Journal of Artificial Intelligence Research 81 (2024) 1623-1701
Decision-focused learning (DFL) is an emerging paradigm that integrates machine learning (ML) and constrained optimization to enhance decision quality by training ML models in an end-to-end system. This approach shows significant potential to revolut
Externí odkaz:
http://arxiv.org/abs/2307.13565
Autor:
Silvestri, Mattia, Berden, Senne, Mandi, Jayanta, Mahmutoğulları, Ali İrfan, Amos, Brandon, Guns, Tias, Lombardi, Michele
Many real-world optimization problems contain parameters that are unknown before deployment time, either due to stochasticity or to lack of information (e.g., demand or travel times in delivery problems). A common strategy in such cases is to estimat
Externí odkaz:
http://arxiv.org/abs/2307.05213
We propose a novel approach to multi-robot collaboration that harnesses the power of pre-trained large language models (LLMs) for both high-level communication and low-level path planning. Robots are equipped with LLMs to discuss and collectively rea
Externí odkaz:
http://arxiv.org/abs/2307.04738
Polarizability is closely related to many fundamental characteristics of molecular systems and plays an indispensable role in simulating the Raman spectra. However, the calculations of polarizability for large systems still suffers from the limitatio
Externí odkaz:
http://arxiv.org/abs/2301.13490