Data Science by ODS.ai 🦜
First Telegram Data Science channel. Covering all technical and popular staff about anything related to Data Science: AI, Big Data, Machine Learning, Statistics, general Math and the applications of former. To reach editors contact: @haarrp
Mostrar más51 733
Suscriptores
+2924 horas
+567 días
+10930 días
Distribuciones de tiempo de publicación
Carga de datos en curso...
Fuentes
Sin datos
¿Algún problema? Por favor, actualice la página o contacte a nuestro gerente de soporte.
Análisis de publicación
Mensajes | Vistas | Acciones | Ver dinámicas |
01 We followed on developing theme in Novemeber 2022. And it looks like we might have another attempt to renew our avatar, what do you think? | 2 004 | 0 | Loading... |
02 This is what we started with and results still look good for 2021. Back in a day we used neural networks for generation of the logo for the channel and it saved us quite some time on communication with designers. | 1 956 | 0 | Loading... |
03 🔥 Say Goodbye to LoRA, Hello to DoRA 🤩🤩
DoRA consistently outperforms LoRA with various tasks (LLM, LVLM, etc.) and backbones (LLaMA, LLaVA, etc.)
[Paper] https://arxiv.org/abs/2402.09353
[Code] https://github.com/NVlabs/DoRA
#Nvidia
#icml #PEFT #lora #ML #ai
@opendatascience | 3 493 | 108 | Loading... |
04 Discover, download, and run local LLMs
LM Studio allows to run #LLM model of your choice locally
Link: https://lmstudio.ai/ | 6 406 | 70 | Loading... |
05 👑Llama 3 is here, with a brand new tokenizer! 🦙
Вышла Llama 3
Meta выпустила новую SOTA Llama 3 в двух версиях на 8B и 70B параметров.
Длина контекста 8К, поддержка 30 языков.
•HF: https://huggingface.co/spaces/ysharma/Chat_with_Meta_llama3_8b
•Blog: https://ai.meta.com/blog/meta-llama-3/
Вы можете потестить 🦙 MetaLlama 3 70B и 🦙 Meta Llama 3 8B с помощью 🔥 бесплатного интерфейса: https://llama3.replicate.dev/
@ai_machinelearning_big_data | 9 720 | 47 | Loading... |
06 ⚡️Map-relative Pose Regression🔥(#CVPR2024 highlight)
For years absolute pose regression did not work. There was some success by massively synthesising scene-specific data. We train scene-agnostic APR and it works.
Paper: https://arxiv.org/abs/2404.09884
Page: https://nianticlabs.github.io/marepo
@opendatascience | 8 998 | 17 | Loading... |
07 🔥 ControlNet++: Improving Conditional Controls
with Efficient Consistency Feedback
Proposes an approach that improves controllable generation by explicitly optimizing pixel-level cycle consistency
proj: https://liming-ai.github.io/ControlNet_Plus_Plus/
abs: https://arxiv.org/abs/2404.07987
@opendatascience | 9 821 | 47 | Loading... |
08 🥔 YaART: Yet Another ART Rendering Technology
💚 This study introduces YaART, a novel production-grade text-to-image cascaded diffusion model aligned to human preferences using Reinforcement Learning from Human Feedback (RLHF).
💜 During the development of YaART, Yandex especially focus on the choices of the model and training dataset sizes, the aspects that were not systematically investigated for text-to-image cascaded diffusion models before.
💖 In particular, researchers comprehensively analyze how these choices affect both the efficiency of the training process and the quality of the generated images, which are highly important in practice.
▪Paper page - https://ya.ru/ai/art/paper-yaart-v1
▪Arxiv - https://arxiv.org/abs/2404.05666
▪Habr - https://habr.com/ru/companies/yandex/articles/805745/
@opendatascience | 9 348 | 31 | Loading... |
09 ⚡️ PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
Significantly improved finetuned perf by simply changing the initialization of LoRA's AB matrix from Gaussian/zero to principal components of W
▪Github: https://github.com/GraphPKU/PiSSA
▪Paper: https://arxiv.org/abs/2404.02948
@opendatascience | 10 233 | 136 | Loading... |
10 ⚡️ Awesome CVPR 2024 Papers, Workshops, Challenges, and Tutorials!
На конференцию 2024 года по компьютерному зрению и распознаванию образов (CVPR) поступило 11 532 статей, из которых только 2 719 были приняты, что составляет около 23,6% от общего числа.
Ниже приведен список лучших докладов, гайдов, статей, семинаров и датасетов с CVPR 2024.
▪Github
@ai_machinelearning_big_data | 8 642 | 49 | Loading... |
11 Objective-Driven AI: Towards AI systems that can learn, remember, reason, and plan
A presentation by Yann Lecun on the #SOTA in #DL
YouTube: https://www.youtube.com/watch?v=MiqLoAZFRSE
Slides: Google Doc
Paper: Open Review
P.S. Stole the post from @chillhousetech | 9 095 | 46 | Loading... |
We followed on developing theme in Novemeber 2022. And it looks like we might have another attempt to renew our avatar, what do you think?
👍 8🥱 6🖕 3👎 1
This is what we started with and results still look good for 2021. Back in a day we used neural networks for generation of the logo for the channel and it saved us quite some time on communication with designers.
👍 3🖕 3❤ 1
Photo unavailableShow in Telegram
🔥 Say Goodbye to LoRA, Hello to DoRA 🤩🤩
DoRA consistently outperforms LoRA with various tasks (LLM, LVLM, etc.) and backbones (LLaMA, LLaVA, etc.)
[Paper] https://arxiv.org/abs/2402.09353
[Code] https://github.com/NVlabs/DoRA
#Nvidia
#icml #PEFT #lora #ML #ai
@opendatascience
👍 22🔥 7🤣 5❤ 3👏 1
Photo unavailableShow in Telegram
Discover, download, and run local LLMs
LM Studio allows to run #LLM model of your choice locally
Link: https://lmstudio.ai/
💯 10👍 4🔥 3
Repost from Machinelearning
00:57
Video unavailableShow in Telegram
👑Llama 3 is here, with a brand new tokenizer! 🦙
Вышла Llama 3
Meta выпустила новую SOTA Llama 3 в двух версиях на 8B и 70B параметров.
Длина контекста 8К, поддержка 30 языков.
•HF: https://huggingface.co/spaces/ysharma/Chat_with_Meta_llama3_8b
•Blog: https://ai.meta.com/blog/meta-llama-3/
Вы можете потестить 🦙 MetaLlama 3 70B и 🦙 Meta Llama 3 8B с помощью 🔥 бесплатного интерфейса: https://llama3.replicate.dev/
@ai_machinelearning_big_data
🔥 17👍 9❤ 7
00:14
Video unavailableShow in Telegram
⚡️Map-relative Pose Regression🔥(#CVPR2024 highlight)
For years absolute pose regression did not work. There was some success by massively synthesising scene-specific data. We train scene-agnostic APR and it works.
Paper: https://arxiv.org/abs/2404.09884
Page: https://nianticlabs.github.io/marepo
@opendatascience
👍 5🔥 5❤ 3
Photo unavailableShow in Telegram
🔥 ControlNet++: Improving Conditional Controls
with Efficient Consistency Feedback
Proposes an approach that improves controllable generation by explicitly optimizing pixel-level cycle consistency
proj: https://liming-ai.github.io/ControlNet_Plus_Plus/
abs: https://arxiv.org/abs/2404.07987
@opendatascience
👍 10🔥 10❤ 3
🥔 YaART: Yet Another ART Rendering Technology
💚 This study introduces YaART, a novel production-grade text-to-image cascaded diffusion model aligned to human preferences using Reinforcement Learning from Human Feedback (RLHF).
💜 During the development of YaART, Yandex especially focus on the choices of the model and training dataset sizes, the aspects that were not systematically investigated for text-to-image cascaded diffusion models before.
💖 In particular, researchers comprehensively analyze how these choices affect both the efficiency of the training process and the quality of the generated images, which are highly important in practice.
▪Paper page - https://ya.ru/ai/art/paper-yaart-v1
▪Arxiv - https://arxiv.org/abs/2404.05666
▪Habr - https://habr.com/ru/companies/yandex/articles/805745/
@opendatascience
Your creative AI assistant to generate ART from textual descriptions
👍 21❤ 9🔥 8💩 4🍌 1🖕 1
Photo unavailableShow in Telegram
⚡️ PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
Significantly improved finetuned perf by simply changing the initialization of LoRA's AB matrix from Gaussian/zero to principal components of W
▪Github: https://github.com/GraphPKU/PiSSA
▪Paper: https://arxiv.org/abs/2404.02948
@opendatascience
🔥 20😁 11👍 4🌭 3❤ 2🍌 2
Repost from Machinelearning
Photo unavailableShow in Telegram
⚡️ Awesome CVPR 2024 Papers, Workshops, Challenges, and Tutorials!
На конференцию 2024 года по компьютерному зрению и распознаванию образов (CVPR) поступило 11 532 статей, из которых только 2 719 были приняты, что составляет около 23,6% от общего числа.
Ниже приведен список лучших докладов, гайдов, статей, семинаров и датасетов с CVPR 2024.
▪Github
@ai_machinelearning_big_data
🔥 12👍 5❤ 3