Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Agrawal, Aakriti"'
Autor:
Agrawal, Aakriti, Ding, Mucong, Che, Zora, Deng, Chenghao, Satheesh, Anirudh, Langford, John, Huang, Furong
How can we harness the collective capabilities of multiple Large Language Models (LLMs) to create an even more powerful model? This question forms the foundation of our research, where we propose an innovative approach to weak-to-strong (w2s) general
Externí odkaz:
http://arxiv.org/abs/2410.04571
Autor:
Ding, Mucong, Deng, Chenghao, Choo, Jocelyn, Wu, Zichu, Agrawal, Aakriti, Schwarzschild, Avi, Zhou, Tianyi, Goldstein, Tom, Langford, John, Anandkumar, Anima, Huang, Furong
While generalization over tasks from easy to hard is crucial to profile language models (LLMs), the datasets with fine-grained difficulty annotations for each problem across a broad range of complexity are still blank. Aiming to address this limitati
Externí odkaz:
http://arxiv.org/abs/2409.18433
Autor:
An, Bang, Ding, Mucong, Rabbani, Tahseen, Agrawal, Aakriti, Xu, Yuancheng, Deng, Chenghao, Zhu, Sicheng, Mohamed, Abdirisak, Wen, Yuxin, Goldstein, Tom, Huang, Furong
In the burgeoning age of generative AI, watermarks act as identifiers of provenance and artificial content. We present WAVES (Watermark Analysis Via Enhanced Stress-testing), a benchmark for assessing image watermark robustness, overcoming the limita
Externí odkaz:
http://arxiv.org/abs/2401.08573
Multi-agent reinforcement learning (MARL) plays a pivotal role in tackling real-world challenges. However, the seamless transition of trained policies from simulations to real-world requires it to be robust to various environmental uncertainties. Exi
Externí odkaz:
http://arxiv.org/abs/2310.08746
Publikováno v:
Proc. Interspeech, Aug. 2023, pp. 381-385
Automatic speech recognition (ASR) training can utilize multiple experts as teacher models, each trained on a specific domain or accent. Teacher models may be opaque in nature since their architecture may be not be known or their training cadence is
Externí odkaz:
http://arxiv.org/abs/2306.12012
Publikováno v:
ICRA 2023
We present a novel reinforcement learning based algorithm for multi-robot task allocation problem in warehouse environments. We formulate it as a Markov Decision Process and solve via a novel deep multi-agent reinforcement learning method (called RTA
Externí odkaz:
http://arxiv.org/abs/2209.05738
Publikováno v:
IROS-2022
We present a novel reinforcement learning (RL) based task allocation and decentralized navigation algorithm for mobile robots in warehouse environments. Our approach is designed for scenarios in which multiple robots are used to perform various pick
Externí odkaz:
http://arxiv.org/abs/2209.02865
Autor:
Agrawal, Aakriti, Bhise, Aashay, Arasanipalai, Rohitkumar, Tony, Lima Agnel, Jana, Shuvrangshu, Ghose, Debasish
Accurate estimation and prediction of trajectory is essential for the capture of any high speed target. In this paper, an extended Kalman filter (EKF) is used to track the target in the first loop of the trajectory to collect data points and then a c
Externí odkaz:
http://arxiv.org/abs/2009.00067
A terrestrial robot that can maneuver rough terrain and scout places is very useful in mapping out unknown areas. It can also be used explore dangerous areas in place of humans. A terrestrial robot modeled after a scorpion will be able to traverse un
Externí odkaz:
http://arxiv.org/abs/2008.13712
Parameter sharing, where each agent independently learns a policy with fully shared parameters between all policies, is a popular baseline method for multi-agent deep reinforcement learning. Unfortunately, since all agents share the same policy netwo
Externí odkaz:
http://arxiv.org/abs/2005.13625