Zobrazeno 1 - 10
of 250
pro vyhledávání: '"Yu, Felix"'
Autor:
Yen, Jui-Nan, Si, Si, Meng, Zhao, Yu, Felix, Duvvuri, Sai Surya, Dhillon, Inderjit S., Hsieh, Cho-Jui, Kumar, Sanjiv
Low-rank adaption (LoRA) is a widely used parameter-efficient finetuning method for LLM that reduces memory requirements. However, current LoRA optimizers lack transformation invariance, meaning the actual updates to the weights depends on how the tw
Externí odkaz:
http://arxiv.org/abs/2410.20625
Neutrino telescopes detect rare interactions of particles produced in some of the most extreme environments in the Universe. This is accomplished by instrumenting a cubic-kilometer volume of naturally occurring transparent medium with light sensors.
Externí odkaz:
http://arxiv.org/abs/2410.13148
Our goal is a mechanism for efficiently assigning scalar ratings to each of a large set of elements. For example, "what percent positive or negative is this product review?" When sample sizes are small, prior work has advocated for methods such as Be
Externí odkaz:
http://arxiv.org/abs/2408.09765
Recent discoveries by neutrino telescopes, such as the IceCube Neutrino Observatory, relied extensively on machine learning (ML) tools to infer physical quantities from the raw photon hits detected. Neutrino telescope reconstruction algorithms are li
Externí odkaz:
http://arxiv.org/abs/2408.08474
Autor:
Ji, Ziwei, Jain, Himanshu, Veit, Andreas, Reddi, Sashank J., Jayasumana, Sadeep, Rawat, Ankit Singh, Menon, Aditya Krishna, Yu, Felix, Kumar, Sanjiv
Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized query and d
Externí odkaz:
http://arxiv.org/abs/2406.17968
The trade-off between expressiveness and interpretability remains a core challenge when building human-centric predictive models for classification and decision-making. While symbolic rules offer interpretability, they often lack expressiveness, wher
Externí odkaz:
http://arxiv.org/abs/2406.17224
Autor:
Chiatto, Prisco Lo, Yu, Felix
Extracting constraints on kinetic mixing between a new $U(1)'$ gauge boson hiding under the Standard Model $Z$ boson resonance requires the formalism of non-Hermitian two-point correlation functions at 1-loop order. We derive self-consistent collider
Externí odkaz:
http://arxiv.org/abs/2405.03396
Publikováno v:
EMNLP Findings 2024
Large language models (LLMs) have shown strong results on a range of applications, including regression and scoring tasks. Typically, one obtains outputs from an LLM via autoregressive sampling from the model's output distribution. We show that this
Externí odkaz:
http://arxiv.org/abs/2403.04182
Autor:
Aksitov, Renat, Miryoosefi, Sobhan, Li, Zonglin, Li, Daliang, Babayan, Sheila, Kopparapu, Kavya, Fisher, Zachary, Guo, Ruiqi, Prakash, Sushant, Srinivasan, Pranesh, Zaheer, Manzil, Yu, Felix, Kumar, Sanjiv
Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These systems, ho
Externí odkaz:
http://arxiv.org/abs/2312.10003
Large language models (LLMs) have demonstrated remarkable capabilities in solving complex open-domain tasks, guided by comprehensive instructions and demonstrations provided in the form of prompts. However, these prompts can be lengthy, often compris
Externí odkaz:
http://arxiv.org/abs/2311.10117