SLAY-ASR, или как я перестал волноваться и полюбил тренировать модели Как добавить аудио-модальность в LLMку мак...

#representation #learning #multimodality #multimodal #llm #machine #learning #audio-modality #regularization #contrastive #learning

Origin | Interest | Match

Contrastive Learning Contrastive learning is a powerful technique in machine learning that learns by comparing and contrasting data points.

#ITByte: #Contrastive #Learning is a powerful technique in machine learning that learns by comparing and contrasting data points.

It is used in different domains including Computer Vision and Natural Language Processing.

knowledgezone.co.in/posts/Contra...

Understanding Self-supervised Contrastive Learning through Supervised Objectives

Byeongchan Lee

Action editor: Han Bao

https://openreview.net/forum?id=cmE97KX2XM

#supervised #contrastive #representation

MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation

Yihan Wang, Yiwei Lu, Guojun Zhang et al.

Action editor: Eleni Triantafillou

https://openreview.net/forum?id=F9pjSDvuM9

#unlearning #contrastive #classification

Towards Efficient Contrastive PAC Learning

Jie Shen

Action editor: Tianbao Yang

https://openreview.net/forum?id=dBJo9hyKVg

#contrastive #rademacher #generalization

Contrastive Noise Optimization Improves Text-to-Image Diversity

Contrastive Noise Optimization reshapes the random seed of text‑to‑image diffusion models, boosting image diversity and achieving higher diversity scores across backbones. Read more: getnews.me/contrastive-noise-optimi... #contrastive #diffusion

Similarity‑Dissimilarity Loss Improves Multi‑label Contrastive Learning

A new Similarity‑Dissimilarity Loss weights multi‑label contrastive pairs by shared and differing tags, yielding state‑of‑the‑art performance on the MIMIC‑III‑Full medical dataset. Read more: getnews.me/similarity-dissimilarity... #ml #contrastive

GPLASC Contrastive Strategy Boosts Continual Learning Performance

GPLASC splits the representation hypersphere into non‑overlapping ETF regions, boosting retention on benchmark continual‑learning tasks. Read more: getnews.me/gplasc-contrastive-strat... #continuallearning #contrastive

Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs D...

Ruijie Jiang, Thuan Nguyen, Shuchin Aeron, Prakash Ishwar

Action editor: Zhihui Zhu

https://openreview.net/forum?id=3cnpZ5SIjU

#minimized #contrastive #representations

Contrastive Learning Contrastive learning is a powerful technique in machine learning that learns by comparing and contrasting data points.

#ITByte: #Contrastive #Learning is a powerful technique in machine learning that learns by comparing and contrasting data points.

It is used in different domains including Computer Vision and Natural Language Processing.

knowledgezone.co.in/posts/Contra...

GRAM is going to #ICLR2025!
More on this soon, and see y'all in Singapore!
#multimodal #contrastive #learning

Contrastive Learning with Consistent Representations

Zihu Wang, Yu Wang, Zhuotong Chen, Hanbin Hu, Peng Li

Action editor: Mathieu Salzmann

https://openreview.net/forum?id=gKeSI8w63Z

#representations #contrastive #augmentation