Zobrazeno 1 - 10
of 144
pro vyhledávání: '"Lazar, Daniel A"'
Autor:
Le, Trang, Lazar, Daniel, Kim, Suyoun, Jiang, Shan, Le, Duc, Sagar, Adithya, Livshits, Aleksandr, Aly, Ahmed, Shrivastava, Akshat
Spoken Language Understanding (SLU) is a critical component of voice assistants; it consists of converting speech to semantic parses for task execution. Previous works have explored end-to-end models to improve the quality and robustness of SLU model
Externí odkaz:
http://arxiv.org/abs/2406.07823
Autor:
Hou, Charlie, Shrivastava, Akshat, Zhan, Hongyuan, Conway, Rylan, Le, Trang, Sagar, Adithya, Fanti, Giulia, Lazar, Daniel
On-device training is currently the most common approach for training machine learning (ML) models on private, distributed user data. Despite this, on-device training has several drawbacks: (1) most user devices are too small to train large models on
Externí odkaz:
http://arxiv.org/abs/2406.02958
Autor:
Sharma, Roshan, Kim, Suyoun, Lazar, Daniel, Le, Trang, Shrivastava, Akshat, Ahn, Kwanghoon, Kansal, Piyush, Sari, Leda, Kalinli, Ozlem, Seltzer, Michael
Spoken semantic parsing (SSP) involves generating machine-comprehensible parses from input speech. Training robust models for existing application domains represented in training data or extending to new domains requires corresponding triplets of spe
Externí odkaz:
http://arxiv.org/abs/2309.09390
Autor:
Hou, Charlie, Zhan, Hongyuan, Shrivastava, Akshat, Wang, Sid, Livshits, Aleksandr, Fanti, Giulia, Lazar, Daniel
In Federated Learning (FL), accessing private client data incurs communication and privacy costs. As a result, FL deployments commonly prefinetune pretrained foundation models on a (large, possibly public) dataset that is held by the central server;
Externí odkaz:
http://arxiv.org/abs/2302.09042
Autor:
Tomasello, Paden, Shrivastava, Akshat, Lazar, Daniel, Hsu, Po-Chun, Le, Duc, Sagar, Adithya, Elkahky, Ali, Copet, Jade, Hsu, Wei-Ning, Adi, Yossi, Algayres, Robin, Nguyen, Tu Ahn, Dupoux, Emmanuel, Zettlemoyer, Luke, Mohamed, Abdelrahman
End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual representation an
Externí odkaz:
http://arxiv.org/abs/2207.10643
Autor:
Wang, Woodrow Z., Beliaev, Mark, Bıyık, Erdem, Lazar, Daniel A., Pedarsani, Ramtin, Sadigh, Dorsa
Coordination is often critical to forming prosocial behaviors -- behaviors that increase the overall sum of rewards received by all agents in a multi-agent game. However, state of the art reinforcement learning algorithms often suffer from converging
Externí odkaz:
http://arxiv.org/abs/2105.06593
Traffic congestion has large economic and social costs. The introduction of autonomous vehicles can potentially reduce this congestion by increasing road capacity via vehicle platooning and by creating an avenue for influencing people's choice of rou
Externí odkaz:
http://arxiv.org/abs/2106.04678
Autor:
Lazar, Daniel A., Pedarsani, Ramtin
With autonomous vehicles now sharing roads with human drivers, the era of mixed autonomy brings new challenges in dealing with congestion. One cause of congestion is when vehicle users choose their routes selfishly to minimize their personal travel d
Externí odkaz:
http://arxiv.org/abs/2103.13553
Autor:
Beliaev, Mark, Bıyık, Erdem, Lazar, Daniel A., Wang, Woodrow Z., Sadigh, Dorsa, Pedarsani, Ramtin
The COVID-19 pandemic has severely affected many aspects of people's daily lives. While many countries are in a re-opening stage, some effects of the pandemic on people's behaviors are expected to last much longer, including how they choose between d
Externí odkaz:
http://arxiv.org/abs/2012.15749
Autor:
Lazar, Daniel A., Pedarsani, Ramtin
When selfish users share a road network and minimize their individual travel costs, the equilibrium they reach can be worse than the socially optimal routing. Tolls are often used to mitigate this effect in traditional congestion games, where all veh
Externí odkaz:
http://arxiv.org/abs/2009.00198