Zobrazeno 1 - 10
of 93
pro vyhledávání: '"Melnyk, Igor"'
Autor:
Melnyk, Igor, Mroueh, Youssef, Belgodere, Brian, Rigotti, Mattia, Nitsure, Apoorva, Yurochkin, Mikhail, Greenewald, Kristjan, Navratil, Jiri, Ross, Jerret
Current LLM alignment techniques use pairwise human preferences at a sample level, and as such, they do not imply an alignment on the distributional level. We propose in this paper Alignment via Optimal Transport (AOT), a novel method for distributio
Externí odkaz:
http://arxiv.org/abs/2406.05882
Autor:
Das, Payel, Chaudhury, Subhajit, Nelson, Elliot, Melnyk, Igor, Swaminathan, Sarath, Dai, Sihui, Lozano, Aurélie, Kollias, Georgios, Chenthamarakshan, Vijil, Jiří, Navrátil, Dan, Soham, Chen, Pin-Yu
Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today. This paper presents Larimar - a novel, brain-inspired architecture for enhancing LLMs with a distributed episod
Externí odkaz:
http://arxiv.org/abs/2403.11901
Autor:
Nitsure, Apoorva, Mroueh, Youssef, Rigotti, Mattia, Greenewald, Kristjan, Belgodere, Brian, Yurochkin, Mikhail, Navratil, Jiri, Melnyk, Igor, Ross, Jerret
We propose a distributional framework for benchmarking socio-technical risks of foundation models with quantified statistical significance. Our approach hinges on a new statistical relative testing based on first and second order stochastic dominance
Externí odkaz:
http://arxiv.org/abs/2310.07132
Autor:
Belgodere, Brian, Dognin, Pierre, Ivankay, Adam, Melnyk, Igor, Mroueh, Youssef, Mojsilovic, Aleksandra, Navratil, Jiri, Nitsure, Apoorva, Padhi, Inkit, Rigotti, Mattia, Ross, Jerret, Schiff, Yair, Vedpathak, Radhika, Young, Richard A.
Real-world data often exhibits bias, imbalance, and privacy risks. Synthetic datasets have emerged to address these issues. This paradigm relies on generative AI models to generate unbiased, privacy-preserving data while maintaining fidelity to the o
Externí odkaz:
http://arxiv.org/abs/2304.10819
In this work we propose a novel end-to-end multi-stage Knowledge Graph (KG) generation system from textual inputs, separating the overall process into two stages. The graph nodes are generated first using pretrained language model, followed by a simp
Externí odkaz:
http://arxiv.org/abs/2211.10511
Autor:
Melnyk, Igor, Chenthamarakshan, Vijil, Chen, Pin-Yu, Das, Payel, Dhurandhar, Amit, Padhi, Inkit, Das, Devleena
Antibodies comprise the most versatile class of binding molecules, with numerous applications in biomedicine. Computational design of antibodies involves generating novel and diverse sequences, while maintaining structural consistency. Unique to anti
Externí odkaz:
http://arxiv.org/abs/2210.07144
Inverse protein folding, the process of designing sequences that fold into a specific 3D structure, is crucial in bio-engineering and drug discovery. Traditional methods rely on experimentally resolved structures, but these cover only a small fractio
Externí odkaz:
http://arxiv.org/abs/2210.03488
Autor:
Belgodere, Brian, Chenthamarakshan, Vijil, Das, Payel, Dognin, Pierre, Kurien, Toby, Melnyk, Igor, Mroueh, Youssef, Padhi, Inkit, Rigotti, Mattia, Ross, Jarret, Schiff, Yair, Young, Richard A.
With the prospect of automating a number of chemical tasks with high fidelity, chemical language processing models are emerging at a rapid speed. Here, we present a cloud-based real-time platform that allows users to virtually screen molecules of int
Externí odkaz:
http://arxiv.org/abs/2208.06665
Computational protein design, i.e. inferring novel and diverse protein sequences consistent with a given structure, remains a major unsolved challenge. Recently, deep generative models that learn from sequences alone or from sequences and structures
Externí odkaz:
http://arxiv.org/abs/2111.06801
Automatic construction of relevant Knowledge Bases (KBs) from text, and generation of semantically meaningful text from KBs are both long-standing goals in Machine Learning. In this paper, we present ReGen, a bidirectional generation of text and grap
Externí odkaz:
http://arxiv.org/abs/2108.12472