Zobrazeno 1 - 10
of 59
pro vyhledávání: '"SANKARARAMAN, KARTHIK"'
Autor:
Wang, Chaoqi, Zhao, Zhuokai, Zhu, Chen, Sankararaman, Karthik Abinav, Valko, Michal, Cao, Xuefei, Chen, Zhaorun, Khabsa, Madian, Chen, Yuxin, Ma, Hao, Wang, Sinong
Recent advancements in generative models, particularly large language models (LLMs) and diffusion models, have been driven by extensive pretraining on large datasets followed by post-training. However, current post-training methods such as reinforcem
Externí odkaz:
http://arxiv.org/abs/2410.12138
Autor:
Xu, Tengyu, Helenowski, Eryk, Sankararaman, Karthik Abinav, Jin, Di, Peng, Kaiyan, Han, Eric, Nie, Shaoliang, Zhu, Chen, Zhang, Hejia, Zhou, Wenxuan, Zeng, Zhouhao, He, Yun, Mandyam, Karishma, Talabzadeh, Arya, Khabsa, Madian, Cohen, Gabriel, Tian, Yuandong, Ma, Hao, Wang, Sinong, Fang, Han
Reinforcement learning from human feedback (RLHF) has become the leading approach for fine-tuning large language models (LLM). However, RLHF has limitations in multi-task learning (MTL) due to challenges of reward hacking and extreme multi-objective
Externí odkaz:
http://arxiv.org/abs/2409.20370
Autor:
Han, Xiaotian, Zeng, Hanqing, Chen, Yu, Nie, Shaoliang, Liu, Jingzhou, Narang, Kanika, Shakeri, Zahra, Sankararaman, Karthik Abinav, Jiang, Song, Khabsa, Madian, Wang, Qifan, Hu, Xia
This paper investigates the relationship between graph convolution and Mixup techniques. Graph convolution in a graph neural network involves aggregating features from neighboring samples to learn representative features for a specific node or sample
Externí odkaz:
http://arxiv.org/abs/2310.00183
Autor:
Xiong, Wenhan, Liu, Jingyu, Molybog, Igor, Zhang, Hejia, Bhargava, Prajjwal, Hou, Rui, Martin, Louis, Rungta, Rashi, Sankararaman, Karthik Abinav, Oguz, Barlas, Khabsa, Madian, Fang, Han, Mehdad, Yashar, Narang, Sharan, Malik, Kshitiz, Fan, Angela, Bhosale, Shruti, Edunov, Sergey, Lewis, Mike, Wang, Sinong, Ma, Hao
We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our model series are built through continual pretraining from Llama 2 with longer training sequences and on a dataset where long texts are upsampl
Externí odkaz:
http://arxiv.org/abs/2309.16039
Autor:
Yao, Fan, Li, Chuanhao, Sankararaman, Karthik Abinav, Liao, Yiming, Zhu, Yan, Wang, Qifan, Wang, Hongning, Xu, Haifeng
The past decade has witnessed the flourishing of a new profession as media content creators, who rely on revenue streams from online content recommendation platforms. The reward mechanism employed by these platforms creates a competitive environment
Externí odkaz:
http://arxiv.org/abs/2306.07893
We consider contextual bandits with linear constraints (CBwLC), a variant of contextual bandits in which the algorithm consumes multiple resources subject to linear constraints on total consumption. This problem generalizes contextual bandits with kn
Externí odkaz:
http://arxiv.org/abs/2211.07484
Autor:
Chen, Yifang, Sankararaman, Karthik, Lazaric, Alessandro, Pirotta, Matteo, Karamshuk, Dmytro, Wang, Qifan, Mandyam, Karishma, Wang, Sinong, Fang, Han
Active learning with strong and weak labelers considers a practical setting where we have access to both costly but accurate strong labelers and inaccurate but cheap predictions provided by weak labelers. We study this problem in the streaming settin
Externí odkaz:
http://arxiv.org/abs/2211.02233
Transformer has become ubiquitous due to its dominant performance in various NLP and image processing tasks. However, it lacks understanding of how to generate mathematically grounded uncertainty estimates for transformer architectures. Models equipp
Externí odkaz:
http://arxiv.org/abs/2206.00826
We consider Online Minimum Bipartite Matching under the uniform metric. We show that Randomized Greedy achieves a competitive ratio equal to $(1+1/n) (H_{n+1}-1)$, which matches the lower bound. Comparing with the fact that RG achieves an optimal rat
Externí odkaz:
http://arxiv.org/abs/2112.05247
Autor:
McElfresh, Duncan C, Kroer, Christian, Pupyrev, Sergey, Sodomka, Eric, Sankararaman, Karthik, Chauvin, Zack, Dexter, Neil, Dickerson, John P
Global demand for donated blood far exceeds supply, and unmet need is greatest in low- and middle-income countries; experts suggest that large-scale coordination is necessary to alleviate demand. Using the Facebook Blood Donation tool, we conduct the
Externí odkaz:
http://arxiv.org/abs/2108.04862