繁體中文
English Indonesia Türkçe Deutsch Español Português Pусский Français Italiano Nederlands Polski العربية ไทย Tiếng Việt 繁體中文 简体中文 日本語 한국어

#aianddeeplearningapplications 搜尋結果

未找到 "#aianddeeplearningapplications" 的結果
PythonPr's profile picture. #python #programming
Python Programming
@PythonPr
年10月29日

Summary chart of deep learning neural networks

PythonPr's tweet image. Summary chart of deep learning neural networks
6
90
517
203
19千
beechinour's profile picture. crashout studios
beech
@beechinour
年10月29日

i’ve tested 99% of AI image generation methods since i started making these videos... 99% of outputs are slop, but me and my team have discovered a few really good frameworks that let’s us create extremely tasteful and high quality images We train our images off of the…

beechinour's tweet image. i’ve tested 99% of AI image generation methods since i started making these videos... 99% of outputs are slop, but me and my team have discovered a few really good frameworks that let’s us create extremely tasteful and high quality images We train our images off of the…
beechinour's tweet image. i’ve tested 99% of AI image generation methods since i started making these videos... 99% of outputs are slop, but me and my team have discovered a few really good frameworks that let’s us create extremely tasteful and high quality images We train our images off of the…
beechinour's tweet image. i’ve tested 99% of AI image generation methods since i started making these videos... 99% of outputs are slop, but me and my team have discovered a few really good frameworks that let’s us create extremely tasteful and high quality images We train our images off of the…
beechinour's tweet image. i’ve tested 99% of AI image generation methods since i started making these videos... 99% of outputs are slop, but me and my team have discovered a few really good frameworks that let’s us create extremely tasteful and high quality images We train our images off of the…
947
625
2千
1千
176千
aiart_green's profile picture. 💚緑髪AI美女のイラスト 💚水着・パジャマ・チア等のコスプレ 💚緑が大好きです 💚フォロー・👍・RP よろしくね 💚AI beauty. cosplay bikini, pajamas, cheers, etc. 💚please follow me 💚#AIart #AIphoto #kawaii
AI美女＠みどり💚 AI beauty @ Green
@aiart_green
6 小時

おはよ～♪ 今日も自分を信じて、胸を張って歩いていこうよ💚 Good morning♪ Believe in yourself and walk forward with confidence🍃 #AIartwork #AIグラビア

aiart_green's tweet image. おはよ～♪ 今日も自分を信じて、胸を張って歩いていこうよ💚 Good morning♪ Believe in yourself and walk forward with confidence🍃 #AIartwork #AIグラビア
9
3
28
1
248
awinyimgprocess's profile picture. Tenure-track Professor in Central South University， NUS PHD. Focus on Multi-modality Learning and Data-centric AI.
Jinpeng Wang
@awinyimgprocess
年10月21日

DeepSeek-OCR looks impressive, but its core idea is not new. Input “Text” as “Image” — already explored by: LANGUAGE MODELING WITH PIXELS (Phillip et al., ICLR 2023) CLIPPO: Image-and-Language Understanding from Pixels Only (Michael et al. CVPR 2023) Pix2Struct: Screenshot…

awinyimgprocess's tweet image. DeepSeek-OCR looks impressive, but its core idea is not new. Input “Text” as “Image” — already explored by: LANGUAGE MODELING WITH PIXELS (Phillip et al., ICLR 2023) CLIPPO: Image-and-Language Understanding from Pixels Only (Michael et al. CVPR 2023) Pix2Struct: Screenshot…
awinyimgprocess's tweet image. DeepSeek-OCR looks impressive, but its core idea is not new. Input “Text” as “Image” — already explored by: LANGUAGE MODELING WITH PIXELS (Phillip et al., ICLR 2023) CLIPPO: Image-and-Language Understanding from Pixels Only (Michael et al. CVPR 2023) Pix2Struct: Screenshot…
awinyimgprocess's tweet image. DeepSeek-OCR looks impressive, but its core idea is not new. Input “Text” as “Image” — already explored by: LANGUAGE MODELING WITH PIXELS (Phillip et al., ICLR 2023) CLIPPO: Image-and-Language Understanding from Pixels Only (Michael et al. CVPR 2023) Pix2Struct: Screenshot…
awinyimgprocess's tweet image. DeepSeek-OCR looks impressive, but its core idea is not new. Input “Text” as “Image” — already explored by: LANGUAGE MODELING WITH PIXELS (Phillip et al., ICLR 2023) CLIPPO: Image-and-Language Understanding from Pixels Only (Michael et al. CVPR 2023) Pix2Struct: Screenshot…
27
42
391
193
41千
AtnsXBT's profile picture. Azuki ⛩️ ⠀⠀⠀⠀⠈⠐⠶⣦⣄⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀ ⢀⣀⣤⣤⣤⣤⣄⣈⣿⣿⢿⣶⣄⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣀⣠⡴⠊ ⠈⠙⠟⣏⠉⢋⢻⡚⠏⠛⢷⣌⡙⠻⠗⠀⠀⠀⠀⠀⠀⣀⣴⡿⢯⣥⡄⠀ ⠀⠀⠀⠸⢳⣦⣭⣄⣤⣤⡬⠟⠉⠁⠀⠀⠀⠀⠀⢠⣚⠿⠋⢀⣴⠉⠁⠀ ⠀⠀⠀⠀⠀⠈⠙⠙⠉⠉⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠘⠛⠛⠛⠁⠀⠀⠀
AtnsMDX
@AtnsXBT
16 小時

Quick tips for using AI to make banger images for your or others PFPs: <> Chatgpt. Better for creating images with sceneries <> Gemini. Better for creating specific adjustments ( Making your pfp bald or make it hold something ) Bookmark this 2 images for comparison

AtnsXBT's tweet image. Quick tips for using AI to make banger images for your or others PFPs: &amp;lt;&amp;gt; Chatgpt. Better for creating images with sceneries &amp;lt;&amp;gt; Gemini. Better for creating specific adjustments ( Making your pfp bald or make it hold something ) Bookmark this 2 images for comparison
AtnsXBT's tweet image. Quick tips for using AI to make banger images for your or others PFPs: &amp;lt;&amp;gt; Chatgpt. Better for creating images with sceneries &amp;lt;&amp;gt; Gemini. Better for creating specific adjustments ( Making your pfp bald or make it hold something ) Bookmark this 2 images for comparison
50
0
79
16
1千
PythonPr's profile picture. #python #programming
Python Programming
@PythonPr
年10月4日

Convolutional Neural Networks | Deep Learning

PythonPr's tweet image. Convolutional Neural Networks | Deep Learning
3
92
517
192
20千
MokadyRon's profile picture. Visual Generative Models Research lead @ BRIA AI
Ron Mokady
@MokadyRon
年10月29日

Generating an image from 1,000 words. Very excited to release Fibo 😃, the first ever open-source model trained exclusively on long, structured captions. Fibo sets a new standard for controllability and disentanglement in image generation [1/6] 🧵

MokadyRon's tweet image. Generating an image from 1,000 words. Very excited to release Fibo 😃, the first ever open-source model trained exclusively on long, structured captions. Fibo sets a new standard for controllability and disentanglement in image generation [1/6] 🧵
20
52
438
277
42千
AIwithSafia's profile picture. Future of AI | Business & Tech | 3K on LinkedIn | Content & Prompts for career growth | Open for collabs—DM me
Safia Sultana
@AIwithSafia
年10月28日

Still only using ChatGPT? That’s like using a flip phone in the iPhone era. These 12 tools will blow your mind.⤵️

AIwithSafia's tweet image. Still only using ChatGPT? That’s like using a flip phone in the iPhone era. These 12 tools will blow your mind.⤵️
39
20
54
10
2千
pharlow28's profile picture. AI Automation Specialist 🤖 — I help busy teams automate tasks using AI + no-code tools like n8n, Make, Airtable, Zapier & Notion | Virtual Assistant
big pharlow
 @pharlow28
9 小時

Upload an empty room photo. Get 5 interior design versions instantly. Built this AI Home Staging workflow on n8n using Telegram + AI image model. Perfect for realtors, designers & home staging pros. @n8n_io @omoalhajaabiola @skill_afrika_

pharlow28's tweet image. Upload an empty room photo. Get 5 interior design versions instantly. Built this AI Home Staging workflow on n8n using Telegram + AI image model. Perfect for realtors, designers &amp;amp; home staging pros. @n8n_io @omoalhajaabiola @skill_afrika_
pharlow28's tweet image. Upload an empty room photo. Get 5 interior design versions instantly. Built this AI Home Staging workflow on n8n using Telegram + AI image model. Perfect for realtors, designers &amp;amp; home staging pros. @n8n_io @omoalhajaabiola @skill_afrika_
pharlow28's tweet image. Upload an empty room photo. Get 5 interior design versions instantly. Built this AI Home Staging workflow on n8n using Telegram + AI image model. Perfect for realtors, designers &amp;amp; home staging pros. @n8n_io @omoalhajaabiola @skill_afrika_
pharlow28's tweet image. Upload an empty room photo. Get 5 interior design versions instantly. Built this AI Home Staging workflow on n8n using Telegram + AI image model. Perfect for realtors, designers &amp;amp; home staging pros. @n8n_io @omoalhajaabiola @skill_afrika_
12
13
67
77
11千
joyceericaa's profile picture. || $Crypto Enthusiast || 👸🏽|| WEB 3 || SOL ||💎||Collab Manager||Alpha Hunter ||Loner 🫥🫥🫥🫥
Joyce❤️
 @joyceericaa
年10月28日

Want to make gorgeous AI pictures for nothing? 1. Open Gemini 2. Post a photo of yourself 3. Add your prompt. Watch the magic happen ✨ GN🫡 #GeminiAI #AIart #AIphotography #AestheticAI #CinematicAI #GN #BamBam

joyceericaa's tweet image. Want to make gorgeous AI pictures for nothing? 1. Open Gemini 2. Post a photo of yourself 3. Add your prompt. Watch the magic happen ✨ GN🫡 #GeminiAI #AIart #AIphotography #AestheticAI #CinematicAI #GN #BamBam
joyceericaa's tweet image. Want to make gorgeous AI pictures for nothing? 1. Open Gemini 2. Post a photo of yourself 3. Add your prompt. Watch the magic happen ✨ GN🫡 #GeminiAI #AIart #AIphotography #AestheticAI #CinematicAI #GN #BamBam
7
0
19
1
742
godofprompt's profile picture. 🔑 Sharing AI Prompts, Tips & Tricks. The Biggest Collection of AI Prompts & Guides for ChatGPT, Grok, Claude & Midjourney AI → https://t.co/vwZZ2VSfsN
God of Prompt
@godofprompt
年10月20日

🚨 DeepSeek just did something wild. They built an OCR system that compresses long text into vision tokens literally turning paragraphs into pixels. Their model, DeepSeek-OCR, achieves 97% decoding precision at 10× compression and still manages 60% accuracy even at 20×. That…

godofprompt's tweet image. 🚨 DeepSeek just did something wild. They built an OCR system that compresses long text into vision tokens literally turning paragraphs into pixels. Their model, DeepSeek-OCR, achieves 97% decoding precision at 10× compression and still manages 60% accuracy even at 20×. That…
252
2千
11千
5千
949千
PolySketch303's profile picture. AIGeneratedArt イラスト ◆ AdobeFireflyとphotoshopで制作　 お仕事は、お堅い3DCG制作　 子持ちのおっさんですが。。 その内作品どこかにまとめたいなあ
polyskech303
@PolySketch303
18 分鐘

曲線と光/FuturisticDesign / AIart / AdobeFirefly /#AIArchitecture

PolySketch303's tweet image. 曲線と光/FuturisticDesign / AIart / AdobeFirefly /#AIArchitecture
PolySketch303's profile picture. AIGeneratedArt イラスト ◆ AdobeFireflyとphotoshopで制作　 お仕事は、お堅い3DCG制作　 子持ちのおっさんですが。。 その内作品どこかにまとめたいなあ
polyskech303
@PolySketch303
年10月29日

Adobe　ファイアフライが アップデートされたので 夢中で遊んでました✨✨ 建築写真、うまくやればできそうな気がする たのしいｗｗｗｗ おやすみいい✨ / AIart / AdobeFirefly /

PolySketch303's tweet image. Adobe　ファイアフライが アップデートされたので 夢中で遊んでました✨✨ 建築写真、うまくやればできそうな気がする たのしいｗｗｗｗ おやすみいい✨ / AIart / AdobeFirefly /
2
14
143
0
3千
1
1
5
0
53
vllm_project's profile picture. A high-throughput and memory-efficient inference and serving engine for LLMs. Join https://t.co/lxJ0SfX5pJ to discuss together with the community!
vLLM
@vllm_project
年10月20日

🚀 DeepSeek-OCR — the new frontier of OCR from @deepseek_ai , exploring optical context compression for LLMs, is running blazingly fast on vLLM ⚡ (~2500 tokens/s on A100-40G) — powered by vllm==0.8.5 for day-0 model support. 🧠 Compresses visual contexts up to 20× while keeping…

vllm_project's tweet image. 🚀 DeepSeek-OCR — the new frontier of OCR from @deepseek_ai , exploring optical context compression for LLMs, is running blazingly fast on vLLM ⚡ (~2500 tokens/s on A100-40G) — powered by vllm==0.8.5 for day-0 model support. 🧠 Compresses visual contexts up to 20× while keeping…
vllm_project's tweet image. 🚀 DeepSeek-OCR — the new frontier of OCR from @deepseek_ai , exploring optical context compression for LLMs, is running blazingly fast on vLLM ⚡ (~2500 tokens/s on A100-40G) — powered by vllm==0.8.5 for day-0 model support. 🧠 Compresses visual contexts up to 20× while keeping…
vllm_project's tweet image. 🚀 DeepSeek-OCR — the new frontier of OCR from @deepseek_ai , exploring optical context compression for LLMs, is running blazingly fast on vLLM ⚡ (~2500 tokens/s on A100-40G) — powered by vllm==0.8.5 for day-0 model support. 🧠 Compresses visual contexts up to 20× while keeping…
49
379
3千
1千
1.4百萬
Kangwook_Lee's profile picture. UW Madison / KRAFTON AI
Kangwook Lee
@Kangwook_Lee
年10月21日

A more serious thread on the DeepSeek-OCR hype / serious misinterpretation going on. 1. On token reduction via representing text in images, researchers from Cambridge have previously shown that 500x prompt token compression is possible (ACL'25, Li, Su, and Collier). Without…

Kangwook_Lee's tweet image. A more serious thread on the DeepSeek-OCR hype / serious misinterpretation going on. 1. On token reduction via representing text in images, researchers from Cambridge have previously shown that 500x prompt token compression is possible (ACL&apos;25, Li, Su, and Collier). Without…
Kangwook_Lee's tweet image. A more serious thread on the DeepSeek-OCR hype / serious misinterpretation going on. 1. On token reduction via representing text in images, researchers from Cambridge have previously shown that 500x prompt token compression is possible (ACL&apos;25, Li, Su, and Collier). Without…
Kangwook_Lee's tweet image. A more serious thread on the DeepSeek-OCR hype / serious misinterpretation going on. 1. On token reduction via representing text in images, researchers from Cambridge have previously shown that 500x prompt token compression is possible (ACL&apos;25, Li, Su, and Collier). Without…
13
80
557
553
87千
_akhaliq's profile picture. AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo ,submit papers here: https://t.co/UzmYN5YmrQ
AK
@_akhaliq
年10月20日

DeepSeek-OCR Contexts Optical Compression

_akhaliq's tweet image. DeepSeek-OCR Contexts Optical Compression
12
55
470
113
43千
Hesamation's profile picture. AI Engineer • giving birth to agents @CamelAIOrg
ℏεsam
@Hesamation
年12月16日

Deep Learning for computer vision, by Andrej Karpathy CS231n Stanford 2016

Hesamation's tweet image. Deep Learning for computer vision, by Andrej Karpathy CS231n Stanford 2016
1
60
564
324
23千

Something went wrong.


Something went wrong.


United States Trends