linker @keylinker
Working as a DL Reseacher/Engineer in Computer Vision. Dedicated to 'Pierrot', an off-hours experimental research project centered on advanced image generation. github.com/Pierrot-vision… Joined August 2013-
Tweets6K
-
Followers186
-
Following938
-
Likes69
Very exciting work with my amazing collaborators @Hope7Happiness, @Lyy_iiis, Kangyang Zhou, Linrui Ma, and Kaiming He! All code, models, and full training recipe are open-sourced. Blog Post: peppaking8.github.io/#/post/minit2i Code: github.com/PeppaKing8/min… (JAX), github.com/Hope7Happiness… (PyTorch). 🤗 Models: huggingface.co/MiniT2I
. github.com/Pierrot-vision… 문의/질문등은 언제든 환영합니다. 많은 관심 부탁드립니다. 감사합니다.
아직 미완성이지만, 먼저 피에로 코드와 베타 버전 0.8b 학습 모델을 먼저 공개합니다. 계속 업데이트할 계획이며, 완성하는대로 다양한 실험 모델들을 계속 공개할 예정입니다. 자세한 내용(소개/취지/코드/알고리즘등)들은 링크한 레퍼지토리의 README에 상세하게 내용을 써놓았습니다
저 혼자 솔로로 진행하고 있는 이미지 생성 모델 프로젝트 '피에로' 를 소개하고자 합니다. 홀로 개인 비용과 스크래치부터 학습한 모델입니다. 최소한 비용을 학습하기 위해 다양한 알고리즘들을 마구잡이(?)로 적용했습니다.
[주둥이코딩-DL] 논문 리뷰 (계속 업데이트 될 예정) github.com/Pierrot-vision…
Zero training needed, Image-to-LoRA(i2L) V2 is now live 🚀! As a much improved version, the updated i2L can turn one or more reference images into style LoRA in one single forward pass, oblivating the need for explicit training to customize image styles. 🤖 Model Collection: modelscope.ai/collections/Di… 🎠 Studio: modelscope.ai/studios/DiffSy… 📄 Paper: modelscope.ai/papers/2606.13… 🌟 V2 Upgrades: - Compatibility: applicable to various base models including Z-Image, Klein-4B and Hidream-O1. - Speed: Direct style LoRA weights prediction = Zero training. - Style fidelity: High fidelity style transfer, no semantic leakge. - Control: explicit weights unlock asymmetric CFG, multi-reference style fusion, and controllable-generation modules. - Architecture: image encoder + learnable LoRA queries + compressed decoding heads that generate the adapted matrices . It's open. It's out. Go build something cool. 🛠️✨
The Z-Image team publiced their latest paper: High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation Z-image turbo++ 2steps distillation model.
DiP: new pixel-space model, no VAE needed. - Crisp textures without compression artifacts. - 10x faster than prior pixel models - 1.79 FID on ImageNet huggingface.co/zhen-nan/DiP
Andrej Karpathy가 2시간 동안 자기가 실제로 AI를 쓰는 화면을 그대로 보여줬습니다 (OpenAI 공동 창립자, Tesla AI책임자였던) 핵심은 놀라울 정도로 단순합니다 말로 일을 맡기고, 결과를 보고, 다시 한 문장으로 고칩니다 AI 시대의 차이는 프롬프트 암기가 아니라 “일을 맡기는 감각”에서 갈립니다 핵심만 한국어 자막으로 1시간 정도 압축했습니다 AI를 제대로 쓰고 싶은 사람은 꼭 보세요
Andrej Karpathy spent 2h showing how he actually uses AI day to day he's a co-founder of OpenAI and led AI at Tesla, so when he shows how he works, it’s worth watching and the whole session is just him telling the machine what he wants in simple terms, like he's briefing a
Alibaba released Qwen-Image-Flash Few-step distillation goes beyond objectives. Data composition, teacher guidance, and task mixture unlock fast, high-quality text-to-image and instruction-guided editing.
Bytedance drops an interesting paper, Representation Forcing. Understanding and generation meet in a single representation space, learned end to end, with no VAE in between. Looks like VAE will not be necessary for future models. yuqingwang1029.github.io/Representation…
#CVPR2026 paper: It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models Text-to-image models often collapse to near-identical samples. Our fix: optimize the noise. Start from pink 🩷, not white noise. 🔗akoepke.github.io/divgen/index.h… 1/6
We are thrilled to introduce our new work, Representation Forcing for Bottleneck-Free Unified Multimodal Models! What lies between language and pixels? Representation. We propose to ground visual representation in the decoder of a unified model. The decoder learns to predict it from text, just as the encoder reads it from images. Understanding and generation then meet in a single representation space, learned end to end, with no frozen VAE in between. We call this Representation Forcing: the encoder's representations force the decoder to learn the same visual structure, and the decoder's predictions, in turn, force the pixels to follow it. Paper: arxiv.org/abs/2605.31604 Project page: yuqingwang1029.github.io/Representation… Huggingface: huggingface.co/papers/2605.31… Feel free to chat with @yuqingwang1029 at #CVPR2026
What if you could speed up AI image generation by 22x without retraining from scratch? Researchers from Zhejiang University and the University of Adelaide introduce FlashAR. They add a lightweight vertical prediction head to existing autoregressive models, enabling parallel two-way next-token prediction. This preserves the original training objective while dynamically combining horizontal and vertical predictions. Result: up to 22.9x speedup for 512x512 image generation, using just 0.05% of the original training data. FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Project: lxazjk.github.io/FlashAR/ Paper: arxiv.org/abs/2605.09430 Code: github.com/lxazjk/Emu3.5-… Our report: mp.weixin.qq.com/s/k6wry8wpyzOe… 📬 #PapersAccepted by Jiqizhixin
昨日に引き続きブログ公開 Day 2です。 KV cacheの基礎について、「Key, ValueだけcacheしてQueryをcacheしないのはなぜか?」という問いに答える形式でやさしく解説を行いました。 MLエンジニアのための本質から理解するLLM推論 KV cache編|Kazuki Fujii zenn.dev/kaz20/articles…
普段利用しているNVIDIA NGCをGPU Clusterで利用するときの環境構築方法についてTips記事を執筆しました。 Tips: Containerを利用したDL分散学習Libraryの開発環境|Kazuki Fujii zenn.dev/kaz20/articles…
やべぇ、画像生成のデータセットが出た huggingface.co/datasets/jaspe…
JLT: Clean-Latent Prediction in Latent Diffusion Transformers. This is an initial version; we will continue to update it: Paper: arxiv.org/abs/2605.27102 Page: akatsuki-neo.github.io/JLT Code: github.com/akatsuki-neo/J… Model: huggingface.co/dawn-neo/JLT
The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models show what scales: compact semantic structure. We connect them by replacing VAE/RAE decoders with a Pixel Diffusion Decoder. Code and Model available: research.nvidia.com/labs/sil/proje… 🧵(1/N)
PiD + Flux Klein 9B BASE this is 205x zoomed in. the amount of detail in the skin on a BASE gguf model with NO LoRAs is actually unbelieveable. Flux is great but does struggle with skin textures. pixel space is where it belongs. civitai.com/models/2651727…
SHEIKH OF CRYPTO @lilihart1991
79 Followers 580 Following Bitcoin mining ⛏️ binary options 📈 Forex trading📊 Expert opinion 📉 Online trading 📦 Account manager 🖋️ DM 🧾
Robert Scoble @Scobleizer
588K Followers 51K Following San Francisco/Silicon Valley AI | Robots, holodecks, BCIs, analysis of new things | Ex-Microsoft, Rackspace, Fast Company | Wrote eight books about the future.
サラリーマン投... @Awbeearjoor175
53 Followers 2K Following 【完全無料】 25年の株式投資プロチーム(運用資産500億円以上)が提供:毎日の市場分析レポート + 優良成長株のピックアップ。プロの情報を無料で。まずはお気軽にお問い合わせください。
Leautor @Leautor169696
56 Followers 2K Following
SIMON COWELL ✳️ �... @SIMONCOWEL17581
54 Followers 711 Following English television personality, entrepreneur, and record executive. He has judged on the British television talent competition shows💕💯💯💖
Michel Olvera @michelolzam
212 Followers 1K Following PhD in Computer Science @Inria_Nancy. Researcher in audio at @telecomparis.
Amritansh @amritansh_champ
587 Followers 5K Following Building Continual learning for AGI | Avid reader, Peaceful Warrior, Dreamer, always willing to travel & learn !!
McShote @ShoteMc28539
31 Followers 1K Following I live alone now and enjoy business, traveling, shopping, food and music. I have a calm personality and I hope we can be friends.
백세편살 @directory_anc
3 Followers 66 Following
jw turp @JwTurp2023
11 Followers 142 Following
🧠DUNNO🧠 @playDunno
211 Followers 769 Following 👉 AI Quiz Maker 👈 With Dunno, use #AI to create #engaging #quizzes. Whether for #study, #work, or #entertainment, we bring you the joy of learning together
farai rato @FaraiRato
1 Followers 58 Following
scarllet M @3c662db6f68942a
6 Followers 254 Following
Julian Lopez Baasch @JulianLBaasch
222 Followers 3K Following AI product engineer thinking about agents, systems, and real-world software Building withcontext and AgentArxiv
Muhammad Osama @Ozamaaaaaaa
94 Followers 222 Following
Clémentine Dominé, ... @ClementineDomi6
3K Followers 2K Following PhD @GatsbyUCL MA Theoretical Physics @OfficialUoM @UCLA Prev. @ZuckermanBrain @SapienzaRoma @CERN @EPFL Creator @ArtlovesSci Organiser of @unireps
Bill Psomas @bill_psomas
449 Followers 605 Following #MSCA AI Postdoctoral Researcher at Visual Recognition Group, @CVUTPraha. Photographer. Crossfit freak.
Jeff Liang @LiangJeff95
2K Followers 920 Following 筑梦 @UtopaiStudios. Ex- 煉丹 @AIatMeta @utexasece @Tsinghua_Uni.
Chuang Zhu @zhu_chuang
2K Followers 5K Following Associate Professor of the school of AI, BUPT. Working on #ComputerVision, #MachineLearning, and #ImageProcessing. Please go to " https://t.co/UbU3DuiiqP"
Liliane Momeni @LiliMomeni
1K Followers 700 Following Research Scientist @GoogleDeepmind Paris • prev. PhD @Oxford_VGG w/ Andrew Zisserman
Towards AI @towards_AI
41K Followers 2K Following Making AI accessible to all with our courses, blogs, tutorials, books & community. Since 2019 we helped teach over 400k AI. Now we also help corporate teams.
Justin Turpin @Turpin14Justin
2 Followers 18 Following
ᅠᅠᅠᅠ�... @AiParticles
176 Followers 180 Following ᅠᅠᅠDocumenting the rise of AGI. ᅠᅠᅠSummarizing Novel ML Ideas.
CVSM-Group @bupt_cvsm
271 Followers 932 Following Computer vision and smart medicine (CVSM) group. Focus on #ComputerVision, #MachineLearning, #MedicalImageAnalysis. Homepage: https://t.co/bbhCkzrogU
Martin Görner @martin_gorner
13K Followers 6K Following AI/ML engineer. Previously at Google: Product Manager for Keras and TensorFlow and developer advocate on TPUs. Passionate about democratizing Machine Learning.
Abiria @Abiria14
1K Followers 5K Following
Turing Post @TheTuringPost
86K Followers 9K Following On X we surface the AI research that matters and explain the ideas behind it. In the newsletter, we connect the dots between AI’s past, present, and future ⬇️
Jaeho Lee @jaeho_lee_
528 Followers 569 Following a pedantic ML researcher based in korea. also teaches at postech ee
Giseop Kim @GiseopK
2K Followers 2K Following Assistant Professor at Robotics and Mechatronics Eng, DGIST, South Korea.
Seong Joon Oh @coallaoh
2K Followers 1K Following Professor in Scalable Trustworthy AI @ University of Tübingen | Advisor at Parameter Lab & https://t.co/g2GQF5m0TG
evolvingstuff @evolvingstuff
3K Followers 2K Following I post about machine learning and occasionally some other stuff.
Valentin Gabeur @vgabeur
630 Followers 341 Following Research Scientist @GoogleDeepmind | Prev. Postdoc @MetaAI, PhD @Inria & @GoogleAI
Daniele Malitesta @dmalitesta
709 Followers 965 Following Postdoc @UniLUISS | Prev. Postdoc @UnivParisSaclay, Ph.D. @PolibaOfficial, visited @InfAtEd | Co-organizer @LoGConference | #Graphs #RecSys #Multimodality.
ごはんライス定... @ta_ka_gi_wa
39 Followers 1K Following
Louis Maddox @permutans
2K Followers 4K Following Combinatorially curious. Foreword Deployed Ongineer @Havelock_AI
Seoyeon Stella Yang @codestella
683 Followers 752 Following AI Roboticist Girl 🙌💕 3d Vision / Diffusion / 3d generation / NeRF / Visual localization / Vision AI Phd candidate in Seoul National University @SNUnow👩💻
Taeho Lee @taeh0_lee
401 Followers 434 Following Building Kiro, a Personal Automatic Scanning Robot that turns real books into digital knowledge. Ex: Moonlight @ Corca — 10K MAU, ₩50M/mo
아저씨 ICWp @yhpkorea2005
14K Followers 312 Following ICWp stands for Investing on Changing the World Partners. Slow, Steady and Uptrend.
Bill Brooklyn @BillBrooklyn10
74K Followers 64 Following My philosophy: avoid permanent loss, embrace asymmetric reward, and let winners run. Markets are uncertain, but my process never is.
EquityExplorer @SatyazalaZala
3K Followers 6 Following Click on the link below to receive the latest information 👇🏻👇🏻
Mark Sterling @MarkSterling0
37K Followers 61 Following Full-time professional http://trader. Investments & market insights 📈 Specializing in growth and value balancing to seize market opportunities with precision.
Haoyi Zhu @HaoyiZhu
865 Followers 479 Following Intern @ NVIDIA. Ph.D. student @ USTC. World Model. Ex: NVIDIA / CMU / SJTU SANA-WM https://t.co/H2t8LuZ58G Aether https://t.co/UrcTPqpxPF
Seong Hun Lee @SeongHunLee1
2K Followers 2K Following Postdoc working on 3D vision, SfM, Multiview geometry, etc.
Sabu @SabuCoin
30K Followers 10K Following 코인투자에 관련 중요 #국제뉴스 #국제정세 #분석글 #인텔 $ETH $BTC 이더리움의 수호자 👉 구독 시 필터 없이 코인/크립토 다 알려줌
거인의어깨 @jongy064
22K Followers 6K Following 배우면서 사는게 인생 아닌가요? ESTJ/HR담당자(23.11.1~)/미국주식 장기투자/꿀팁은 하이라이트 참고
Antonio Lupetti @antoniolupetti
7K Followers 57 Following Founder of Algebrica. Building a mathematical knowledge base. Math / AI / DL / NLP
Emergence @PcIOvebbCbTdSTb
2K Followers 118 Following
xAI @xai
2.0M Followers 5 Following
DAIR.AI @dair_ai
126K Followers 1 Following Democratizing AI research, education, and technologies. Learn about AI Agents for FREE at https://t.co/HHXg8rryu4
Ostris @ostrisai
13K Followers 313 Following AI / ML researcher and developer. Creator of AI Toolkit - https://t.co/Thqof0Gxpj Support my work - https://t.co/Isg2EXrP7s
2xDad @2xDad
1K Followers 971 Following 사랑하는 쌍둥이와 고양이2 그리고 보물1호 와이프 함께 살아가는중입니다. 🇰🇷🇺🇸🇮🇳 미국주식과 Ai 그리고 로봇에 관심이많습니다. 다양한일을 하는중입니다. (하이라이트를 확인해주세요.)
James LEE @Drjames1177
20K Followers 116 Following Neurosurgeon. 닥터스 테슬라 투자 클럽 회장. Tesla. Space Xai. AI infra.
Kwang Moo Yi @kwangmoo_yi
5K Followers 255 Following Assistant Professor of Computer Science at the University of British Columbia. I also post my daily finds on arxiv. I also created https://t.co/mr7bj9zpDH
TeslaZoa @TeslaZoa
22K Followers 669 Following Tesla Shareholder & Owner l SpaceX investor l Official Toss Securities Influencer l First Korean to get Korean reply from Elon Musk | X premium +
Nancy Pelosi Stock Tr... @pelositracker
1.7M Followers 706 Following Highlighting Politicians' trades so we can invest alongside. $1.7B invested alongside via @joinAutopilot Download Autopilot to trade like a politician
Sang-Woo Lee @sangwoolee_
341 Followers 71 Following I am independent researcher in London. Until 2024, I served as program leader and executive director at NAVER Cloud, developing HyperCLOVA X and CLOVA X.
Gradio @Gradio
57K Followers 11 Following Build and share machine learning apps in 3 lines of Python. Part of the @Huggingface family 🤗. DMs are open for sharing your gradio app with us for promotion!
Computer Vision News @CompVisionNews
8K Followers 1 Following All the news within the field of Computer Vision, Image Analysis, and Medical Image Analysis, aggregated. This Twitter account is maintained by @helpingtheblind
TestDriven.io @testdrivenio
38K Followers 168 Following Teaching practical programming through real-world applications. Tweets by @MikeHerman and @JanGiacomelli.
Ashkan Mirzaei @ashmrz10
1K Followers 376 Following Building world foundation models (Cosmos) @NVIDIAAI Previously @Snap, @UofT, @samsungresearch Opinions are mine.
PhD Voice - Independe... @PhDVoice
129K Followers 76K Following Amplifying the voices of PhD Students. Tag us with # or @PhDVoice. Runs @PostdocVoice. Free PhD Resources https://t.co/jKq1NNX0ch Independently Run
Paul Graham @paulg
3.5M Followers 794 Following
Python Hub @PythonHub
155K Followers 3 Following News & links about Python programming. Support: https://t.co/z5ihtHB4jY Suggest a Link: https://t.co/gOWyInLqhy
Krea @krea_ai
115K Followers 18 Following delightful creative tools with AI inside – we're hiring! https://t.co/mWn3JiDT0n
fraser @Fraser
14K Followers 267 Following vc at @sparkcapital past: head of product at @openai; co-founder/ceo of an AI startup that was acquired by Airbnb
elvis @omarsar0
308K Followers 867 Following Building self-improving AI @dair_ai • Prev: Meta AI | PhD • Learn about AI Agents for FREE here: https://t.co/P5SA9u54xO
cs.LG Papers @arxiv_cs_LG
832 Followers 2 Following unofficial updates on arXiv cs.LG (computer science. learning) papers -- https://t.co/wszOoOIqEj
cs.CV Papers @arxiv_cs_cv_pr
555 Followers 2 Following unofficial updates on arXiv https://t.co/vLQwS71apO (computer science. computer vision and pattern recognition) papers
午後のarXiv @arxivml
1K Followers 0 Following https://t.co/ZBNrZVbzEn のcs.NE, cs.LG, cs.AI, cs.CV, cs.CL, stat.MLに投稿された毎日の論文を、日本時間の正午から10分間隔でツイートするbotです。試験運用中。
arXiv @arXiv_cs_ir
324 Followers 330 Following unofficial daily arXiv https://t.co/BhdJtpYZaR papers
Real Python @realpython
267K Followers 163 Following Online #Python Training & Expert Community: Tutorials, Video Courses, Books, Quizzes...and More! Join 1M+ Pythonistas at https://t.co/VpjtGxdL7J
교수잡 @kyosujob
2K Followers 1K Following 석사,박사 일자리 정보 공유. 교수,연구원,시간강사,교직원,입학사정관 채용정보와 관련 동향 분석. 콘텐츠는 교수신문이 만드는 http://t.co/fWVgSpXa이 제공합니다.
Imagine-ENPC @ImagineEnpc
1K Followers 201 Following Computer Vision team of LIGM/A3SI @EcoledesPonts ParisTech (ENPC)
Jack Valmadre @jvlmdr
847 Followers 1K Following Previously @TheAIML, @GoogleAI France, @UniofOxford, @QUT, @CSIRO. Opinions (or lack thereof) my own. He/him







































