Results 1 to 10 of about 860,939 (358)
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints [PDF]
International Conference on Learning Representations, 2023 The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.
Chaoqi Wang +4 more
semanticscholar +1 more source
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation [PDF]
International Joint Conference on Artificial Intelligence, 2021 Knowledge distillation (KD), transferring knowledge from a cumbersome teacher model to a lightweight student model, has been investigated to design efficient neural architectures.
Taehyeon Kim +4 more
semanticscholar +1 more source
Aggregate Confusion: The Divergence of ESG Rating
Review of Finance, 2022 This paper investigates the divergence of environmental, social, and governance (ESG) ratings based on data from six prominent ESG rating agencies: KLD, Sustainalytics, Moody’s ESG (Vigeo-Eiris), S&P Global (RobecoSAM), Refinitiv (Asset4), and MSCI. We
Florian Berg +2 more
semanticscholar +1 more source
Aligning Language Models with Preferences through f-divergence Minimization [PDF]
International Conference on Machine Learning, 2023 Aligning language models with preferences can be posed as approximating a target distribution representing some desired behavior. Existing approaches differ both in the functional form of the target distribution and the algorithm used to approximate it ...
Dongyoung Go +5 more
semanticscholar +1 more source
TimeTree 5: An Expanded Resource for Species Divergence Times
Molecular biology and evolution, 2022 We present the fifth edition of the TimeTree of Life resource (TToL5), a product of the timetree of life project that aims to synthesize published molecular timetrees and make evolutionary knowledge easily accessible to all.
Sudhir Kumar +7 more
semanticscholar +1 more source
From Time-Collocated to Leapfrog Fundamental Schemes for ADI and CDI FDTD Methods
Axioms, 2022 The leapfrog schemes have been developed for unconditionally stable alternating-direction implicit (ADI) finite-difference time-domain (FDTD) method, and recently the complying-divergence implicit (CDI) FDTD method.
Eng Leong Tan
doaj +1 more source
Genome Composition and Divergence of the Novel Coronavirus (2019-nCoV) Originating in China
Cell Host and Microbe, 2020 An in-depth annotation of the newly discovered coronavirus (2019-nCoV) genome has revealed differences between 2019-nCoV and severe acute respiratory syndrome (SARS) or SARS-like coronaviruses.
Aiping Wu +15 more
semanticscholar +1 more source
Maximum Density Divergence for Domain Adaptation [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020 Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions.
Jingjing Li +5 more
semanticscholar +1 more source
Aggregate Confusion: The Divergence of ESG Ratings
Social Science Research Network, 2020 This paper investigates the divergence of environmental, social, and governance (ESG) ratings. Based on data from six prominent rating agencies - namely, KLD (MSCI Stats), Sustainalytics, Vigeo Eiris (Moody's), RobecoSAM (SP Global), Asset4 (Refinitiv ...
Florian Berg +2 more
semanticscholar +1 more source
Frontiers in Medicine, 2023 The Latin America region comprises several countries that do not follow harmonized regulatory requirements for drug product (DP) marketing authorization applications (MAA), resulting in customized registration dossiers for each country.
Alva Lucia Alvarez +5 more
doaj +1 more source