Zobrazeno 1 - 10
of 48 868
pro vyhledávání: '"A, Veloso"'
Autor:
Kawawa-Beaudan, Maxime, Sood, Srijan, Palande, Soham, Mani, Ganapathy, Balch, Tucker, Veloso, Manuela
We present a lightweight approach to sequence classification using Ensemble Methods for Hidden Markov Models (HMMs). HMMs offer significant advantages in scenarios with imbalanced or smaller datasets due to their simplicity, interpretability, and eff
Externí odkaz:
http://arxiv.org/abs/2409.07619
In this work we consider a new interpretation of fairness in decision making problems. Building upon existing fairness formulations, we focus on how to reason over fairness from a temporal perspective, taking into account the fairness of a history of
Externí odkaz:
http://arxiv.org/abs/2408.13208
Autor:
Morales, Marianela, Pozanco, Alberto, Canonaco, Giuseppe, Gopalakrishnan, Sriram, Borrajo, Daniel, Veloso, Manuela
Most of the work on learning action models focus on learning the actions' dynamics from input plans. This allows us to specify the valid plans of a planning task. However, very little work focuses on learning action costs, which in turn allows us to
Externí odkaz:
http://arxiv.org/abs/2408.10889
With modern vehicles evolving with more features, services, complex systems, with more sensors, actuators, and processing units, it is essential to think about vehicles not only as means of transportation that may tend towards full autonomy, but also
Externí odkaz:
http://arxiv.org/abs/2407.17287
Autor:
Xu, Mengda, Xu, Zhenjia, Xu, Yinghao, Chi, Cheng, Wetzstein, Gordon, Veloso, Manuela, Song, Shuran
We present Im2Flow2Act, a scalable learning framework that enables robots to acquire manipulation skills from diverse data sources. The key idea behind Im2Flow2Act is to use object flow as the manipulation interface, bridging domain gaps between diff
Externí odkaz:
http://arxiv.org/abs/2407.15208
Autor:
Selvi, Aras, Kreacic, Eleonora, Ghassemi, Mohsen, Potluru, Vamsi, Balch, Tucker, Veloso, Manuela
Empirical risk minimization often fails to provide robustness against adversarial attacks in test data, causing poor out-of-sample performance. Adversarially robust optimization (ARO) has thus emerged as the de facto standard for obtaining models tha
Externí odkaz:
http://arxiv.org/abs/2407.13625
Recent advancements in language modeling have shown promising results when applied to time series data. In particular, fine-tuning pre-trained large language models (LLMs) for time series classification tasks has achieved state-of-the-art (SOTA) perf
Externí odkaz:
http://arxiv.org/abs/2407.06533
In this paper we show that if a path structure has non-vanishing curvature at apoint then it has a canonical reduction to a Z/2Z-structure at a neighbourhood of thatpoint (in many cases it has a canonical parallelism). A simple implication of this re
Externí odkaz:
http://arxiv.org/abs/2406.11509
Publikováno v:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (2023) 7144-7159
A myriad of different Large Language Models (LLMs) face a common challenge in contextually analyzing table question-answering tasks. These challenges are engendered from (1) finite context windows for large tables, (2) multi-faceted discrepancies amo
Externí odkaz:
http://arxiv.org/abs/2406.10803
Autor:
Kariyappa, Sanjay, Lécué, Freddy, Mishra, Saumitra, Pond, Christopher, Magazzeni, Daniele, Veloso, Manuela
This paper proposes Progressive Inference - a framework to compute input attributions to explain the predictions of decoder-only sequence classification models. Our work is based on the insight that the classification head of a decoder-only Transform
Externí odkaz:
http://arxiv.org/abs/2406.02625