Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Gadetsky, Artyom"'
In many practical applications, coarse-grained labels are readily available compared to fine-grained labels that reflect subtle differences between classes. However, existing methods cannot leverage coarse labels to infer fine-grained labels in an un
Externí odkaz:
http://arxiv.org/abs/2406.11070
Foundation vision-language models have enabled remarkable zero-shot transferability of the pre-trained representations to a wide range of downstream tasks. However, to solve a new task, zero-shot transfer still necessitates human guidance to define v
Externí odkaz:
http://arxiv.org/abs/2406.07236
Autor:
Gadetsky, Artyom, Brbic, Maria
We present HUME, a simple model-agnostic framework for inferring human labeling of a given dataset without any external supervision. The key insight behind our approach is that classes defined by many human labelings are linearly separable regardless
Externí odkaz:
http://arxiv.org/abs/2311.02940
Structured latent variables allow incorporating meaningful prior knowledge into deep learning models. However, learning with such variables remains challenging because of their discrete nature. Nowadays, the standard learning approach is to define a
Externí odkaz:
http://arxiv.org/abs/2110.15072
Autor:
Gadetsky, Artyom, Struminsky, Kirill, Robinson, Christopher, Quadrianto, Novi, Vetrov, Dmitry
Learning models with discrete latent variables using stochastic gradient descent remains a challenge due to the high variance of gradient estimates. Modern variance reduction techniques mostly consider categorical distributions and have limited appli
Externí odkaz:
http://arxiv.org/abs/1911.10036
We explore recently introduced definition modeling technique that provided the tool for evaluation of different distributed vector representations of words through modeling dictionary definitions of words. In this work, we study the problem of word a
Externí odkaz:
http://arxiv.org/abs/1806.10090