Zobrazeno 1 - 10
of 4 465
pro vyhledávání: '"P, Vijayaraghavan"'
Autor:
Guo, Anxin, Vijayaraghavan, Aravindan
We consider the problem of learning an arbitrarily-biased ReLU activation (or neuron) over Gaussian marginals with the squared loss objective. Despite the ReLU neuron being the basic building block of modern neural networks, we still do not understan
Externí odkaz:
http://arxiv.org/abs/2411.14349
Retrieval-based question answering systems often suffer from positional bias, leading to suboptimal answer generation. We propose LoRE (Logit-Ranked Retriever Ensemble), a novel approach that improves answer accuracy and relevance by mitigating posit
Externí odkaz:
http://arxiv.org/abs/2410.10042
Autor:
Abreu, Rui, Murali, Vijayaraghavan, Rigby, Peter C, Maddila, Chandra, Sun, Weiyan, Ge, Jun, Chinniah, Kaavya, Mockus, Audris, Mehta, Megh, Nagappan, Nachiappan
Release engineering has traditionally focused on continuously delivering features and bug fixes to users, but at a certain scale, it becomes impossible for a release engineering team to determine what should be released. At Meta's scale, the responsi
Externí odkaz:
http://arxiv.org/abs/2410.06351
Autor:
Maddila, Chandra, Ghorbani, Negar, Jabre, Kosay, Murali, Vijayaraghavan, Kim, Edwin, Thakkar, Parth, Laptev, Nikolay Pavlovich, Harman, Olivia, Hsu, Diana, Abreu, Rui, Rigby, Peter C.
SqlCompose brings generative AI into the data analytics domain. SQL is declarative, has formal table schemas, and is often written in a non-linear manner. We address each of these challenges and develop a set of models that shows the importance of ea
Externí odkaz:
http://arxiv.org/abs/2407.13280
Autor:
Vijayaraghavan, Prashanth, Wang, Hongzhi, Shi, Luyao, Baldwin, Tyler, Beymer, David, Degan, Ehsan
Recently, there has been a growing availability of pre-trained text models on various model repositories. These models greatly reduce the cost of training new models from scratch as they can be fine-tuned for specific tasks or trained on large datase
Externí odkaz:
http://arxiv.org/abs/2406.15476
Circuit topology generation plays a crucial role in the design of electronic circuits, influencing the fundamental functionality of the circuit. In this paper, we introduce CIRCUITSYNTH, a novel approach that harnesses LLMs to facilitate the automate
Externí odkaz:
http://arxiv.org/abs/2407.10977
Autor:
Vijayaraghavan, Prashanth, Shi, Luyao, Ambrogio, Stefano, Mackin, Charles, Nitsure, Apoorva, Beymer, David, Degan, Ehsan
With the unprecedented advancements in Large Language Models (LLMs), their application domains have expanded to include code generation tasks across various programming languages. While significant progress has been made in enhancing LLMs for popular
Externí odkaz:
http://arxiv.org/abs/2406.04379
Strong student models can learn from weaker teachers: when trained on the predictions of a weaker model, a strong pretrained student can learn to correct the weak model's errors and generalize to examples where the teacher is not confident, even when
Externí odkaz:
http://arxiv.org/abs/2405.16043
Autor:
Bakshi, Ainesh, Kothari, Pravesh, Rajendran, Goutham, Tulsiani, Madhur, Vijayaraghavan, Aravindan
A set of high dimensional points $X=\{x_1, x_2,\ldots, x_n\} \subset R^d$ in isotropic position is said to be $\delta$-anti concentrated if for every direction $v$, the fraction of points in $X$ satisfying $|\langle x_i,v \rangle |\leq \delta$ is at
Externí odkaz:
http://arxiv.org/abs/2405.15084
Explainable Recommender Systems is an important field of study which provides reasons behind the suggested recommendations. Explanations with recommender systems are useful for developers while debugging anomalies within the system and for consumers
Externí odkaz:
http://arxiv.org/abs/2405.01855