Manjunath @_ssmanjunath
Joined January 2015-
Tweets218
-
Followers152
-
Following3K
-
Likes1K
Following up on my reasoning model article, I just read the new "s1: Simple Test-Time Scaling" paper, which describes an interesting method for improving reasoning models using a combination of pure supervised finetuning (SFT) and scaling inference compute. In short, their…
Here is Tülu 3 405B 🐫 our open-source post-training model that surpasses the performance of DeepSeek-V3! The last member of the Tülu 3 family demonstrates that our recipe, which includes Reinforcement Learning from Verifiable Rewards (RVLR) scales to 405B - with performance on…
We reproduced DeepSeek R1-Zero in the CountDown game, and it just works Through RL, the 3B base LM develops self-verification and search abilities all on its own You can experience the Ahah moment yourself for < $30 Code: github.com/Jiayi-Pan/Tiny… Here's what we learned 🧵
For those trying to understand @deepseek_ai Group Relative Policy Optimization (GRPO). Here, in simple steps: 1️⃣ Generate multiple outputs for each prompt using the current policy 2️⃣ Score these outputs using a reward model (rule or outcome) 3️⃣ Average the rewards and use it as…
Introducing a high-quality open-preference dataset to further this line of research for image generation. Despite being such an inseparable component for modern image generation, open preference datasets are a rarity! So, we decided to work on one with the community!
The highest-scored paper at ICLR 2025 with full scores, 10, 10, 10, 10! The first time in ICLR history? IC-Light is designed to control image lighting. They managed to collect >10 million images for training illumination editing models, with amazing results on SDXL and Flux…
We just released Pixtral 12B paper on Arxiv: arxiv.org/abs/2410.07073
Physicists think AI is physics. Statisticians think AI is statistics. Mathematicians think AI is mathematics. Psychologists think AI is psychology. Neuroscientists think AI is neuroscience. And they’re all right.
📚Introduction to a new paper "Performance Law of Large Language Models"🤖 This paper presents a new empirical equation that directly predicts the performance (i.e., MMLU score) of LLMs by fitting a law on top of several hyper-parameters ⬇️. Leveraging❗️10 open-source models…
🚀 Scribble SDXL ControlNet with Gradio ImageEditor component works like magic! Check out the model and cool Spaces👇
Llama 3 released! 🚨🔔@AIatMeta just released their best open LLM! 👑🚀 Llama 3 is the next iteration of Llama with a ~10% relative improvement to its predecessor! 🤯 Llama 3 comes in 2 different sizes 8B and 70B with a new extended tokenizer and commercially permissive license!…
The new @MistralAI is now #1 on the openLLM leaderboard. Apache 2.0 license too! 🔥🔥🔥
New Instances, New Region, New Capabilities! 🧠 @Google Cloud is now generally available on @huggingface! 🤗 We are excited to launch @GoogleCloudTech as an official backend for Inference Endpoints, offering you more options to power your Generative AI applications. 🚀 🌍 New…
Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. openai.com/sora Prompt: “Beautiful, snowy…
Code Llama 70B Instruct available in Hugging Chat! 💬 Try and experiment with @AIatMeta new Code Llama 70B for free in the @huggingface chat! 😍 👉 huggingface.co/chat?model=cod… Share your experience in this thread! 🤗
You can now access AI directly from your database! Here is a step-by-step demo that uses GPT-4 to classify customer reviews from a MySQL dataset. And I'm only writing SQL instructions! You have to see it! The model acts as another table in the database. I can query it and join…
Another deep learning breakthrough: Deep TDA, a new algorithm using self-supervised learning, overcomes the limitations of traditional dimensionality reduction algorithms. t-SNE and UMAP have long been the favorites. Deep TDA might change that forever. Here are the details:
Training Diffusion Models with Reinforcement Learning Presents an RL-based framework for training denoising diffusion models to directly optimize a variety of reward functions arxiv.org/abs/2305.13301
New open-source chat-GPT model alert! 🚨 @togethercompute released a new version of their chatGPT-NeoX 20B model with higher quality by fine-tuning on user feedback. 🚀🔥 Demo: huggingface.co/spaces/togethe… Model: huggingface.co/togethercomput…

Marina @Afwipoot488508
44 Followers 2K Following I’m too busy working on my own grass to notice if yours is greener.
Fabian Little @FabianLitt69697
32 Followers 3K Following
Freida @freida_acevedo8
252 Followers 3K Following
HilaryAdams @Fm8k575kryJ291w
11 Followers 587 Following
Gretel, Vega. @Zranor62261
20 Followers 881 Following
Trinh Vg @TrinhVuongKU
154 Followers 758 Following PhD student in CS at Korea University. I am interested in AI and its applications in pathology image analysis.
Harry Anthony @HarryEJAnthony
359 Followers 853 Following PhD (DPhil) student at @UniofOxford @oxengsci | Reliable AI for medical image analysis 🩻
Alma @almaewing98
196 Followers 3K Following
Eefweirgaw @Eefweirgaw9266
31 Followers 2K Following
Sharkoughth @SharkoughthalU
64 Followers 5K Following
Swearrrue @Swearrrue9Kv_c
144 Followers 2K Following
Torerough @Torerough7FBK
298 Followers 7K Following
Kayla @kemppainen_kayl
346 Followers 3K Following
Peathete @peathete20080
7 Followers 498 Following When the time is right and the breeze is not dry, go out for a walk and see different scenery.
Ugumba Kwikima @UKwikima
500 Followers 1K Following Former MUHAS(RSNA GLC) Neuroradiology fellow 2020-2022 Specialist Neuroradiologist,(MD,Mmed,Msc) Muhimbili Orthopaedic Institute Honorary Lecturer MUHAS
Frances @frances37fox
365 Followers 3K Following
Makena mati @makena_mati
935 Followers 2K Following Am real.. A mother 😍 A Cityzen fan all through 💙💙
PureFootball @PureFootball_co
77K Followers 20K Following The voice of football fans. 🚨 Daily news, transfers & stories from across the leagues. | ⚽ Built by fans, for fans.
Barbara @barbaraosburn14
476 Followers 3K Following
KimJack18882961 | INF... @KimJack18882961
19 Followers 224 Following https://t.co/zIKgpQxTJk - Nft Studio token PAINTS - https://t.co/pi0rdL1ueA Official Twitter: @ElonPunkNft Discord: https://t.co/X8eJImfkit
Repository for Women ... @WINRePo1
3K Followers 3K Following To help gender equality in neuroscience, we want to make women visible through a repository, a supportive network and communications about women in sciences.
Toni Perämäki @toniperamaki
9K Followers 8K Following 👨🎤 Rockin' the COO chair at @Valohaiai managed MLOps platform.🦈 Music, sailing, tech, coaching/helping new entrepreneurs out are also close to my ❤️.
Game Of Price @Abhijee55809349
33 Followers 439 Following I am a Professional Trader And Trainer Who Has 8+ Years Of Experience In Stock Market but Purpose of this channel is to give knowledge of stock and stock market
Raghav Mehta @RaghavM93
326 Followers 502 Following PostDoc @ICComputing | Medical Imaging + Machine Learning | PhD from @mcgillu @Mila_Quebec | MS from @iiit_hyderabad | XIntern @MetaAI | Personal views @meh_rag
ISLES-challenge @IslesChallenge
191 Followers 407 Following Ischemic Stroke Lesion Segmentation Challenge #miccai24
maddy mcson @MaddyMcson
636 Followers 4K Following Earn 50-100$ is not bad everyday with out taking risk message me and join to my team to guide and earn with us without hustle!
HITESH HINDUJA @HITESHH1495
57 Followers 641 Following A Learner! Microsoft| Ex-Ola,Quantiphi |Ex-RA ISB Hyd, IIM-A |Ex-Accenture Research, JIO, Godrej-Boyce
The Galaxy Crew @The_Galaxy_Crew
53 Followers 280 Following TGC is a collection of cool 1/1 aliens, 8000 items will be released in different drops, with a first drop price of 0,008 ETH, then price will rise every drop 🚀
Camila González @camgbus
1K Followers 940 Following Postdoc at AIDE Lab @Stanford 🇺🇲 | prev. MEC Lab @TUDarmstadt 🇩🇪 | Continual Learning and Monitoring for MIC | @MiccaiStudents | @ContinualAI | 🇦🇷🏳️🌈
openGTN @openGTN
46 Followers 82 Following Open Ground Truth Training Network is an international research project on simulated MRI for medical image analysis, funded by Marie Curie ITN-EID program.
Informatics4life @I4L_org
200 Followers 392 Following Research consortium focusing on big data analysis, AI, computer modeling of disease processes, bioinformatics and implementation in clinical application.
Yixiao Ge @ge_yixiao
2K Followers 782 Following Research Director @XPENGRobotics @XPengMotors. We are hiring!🦾 Previously Principal Researcher @TencentGlobal. PhD from MMLab @CUHKofficial.
Roberto Paolella @RobertoPaolella
83 Followers 182 Following Industrial PhD student at Icometrix. Marie Curie Fellow at University of Antwerp.
Seong Hun Lee @SeongHunLee1
2K Followers 2K Following Postdoc working on 3D vision, SfM, Multiview geometry, etc.
Texas Robotics @texas_robotics
1K Followers 157 Following Texas Robotics unites robotics efforts at @UTAustin with goals to enable deeper collaborations that accelerate and grow research programs.
Wenting Zhao @wzhao_nlp
5K Followers 606 Following reasoning & llms @Alibaba_Qwen Opinions are my own
Wenyan Li @Wenyan62
270 Followers 196 Following PhD student at the CoAStaL NLP Group, University of Copenhagen. Former researcher at Comcast AI and SenseTime.
Haoyu Xiong @CoRL @Haoyu_Xiong_
3K Followers 2K Following PhD student @MIT_CSAIL @MITEECS | Prev @Stanford @CMU_Robotics #Robot_Learning
Dwarkesh Patel @dwarkesh_sp
129K Followers 916 Following Host of @dwarkeshpodcast https://t.co/3SXlu7fy6N https://t.co/4DPAxODFYi https://t.co/hQfIWdM1Un
Nouha Dziri @nouhadziri
5K Followers 690 Following Research Scientist @allen_ai, PhD in NLP 🤖 UofA. Ex @GoogleDeepMind @MSFTResearch @MilaQuebec 🚨🚨 NEW BLOG about LLMs reasoning: https://t.co/Ox0iOaqY7e
maharshi @mrsiipa
41K Followers 864 Following ml perf @fal - learning deeply about life one gradient step at a time - personal blog: https://t.co/TYdFfUBImf
Standard Kernel Co. @Standard_Kernel
799 Followers 1 Following Building AI Infrastructure with AI; fast kernels go brrr
Anne Ouyang @anneouyang
7K Followers 926 Following Building @Standard_Kernel, CS PhD student @Stanford | prev: cuDNN @Nvidia, M.Eng, B.S. in CS @MIT | efficient scalable self-improving AI systems | 🌽KernelBench
Jason Ma @JasonMa2020
5K Followers 1K Following Co-founder @DynaRobotics Prev: @GoogleDeepMind, @NVIDIAAI, @MetaAI, @Penn, @Harvard.
Lindon Gao @Lindon_Gao
947 Followers 17 Following Cofounder & CEO @DynaRobotics, Caper AI ($350m exit)
Dyna Robotics @DynaRobotics
4K Followers 6 Following General and robust AI robots that power the future of the physical economy.
Boyuan Chen @BoyuanChen0
4K Followers 507 Following Researcher @OpenAI, core member of GPT image generation and member of Sora video generation. PhD @MITEECS. I do world models, RL, and robotics.
Tai Wang @wangtai97
834 Followers 491 Following Research Scientist at Shanghai AI Lab. Embodied AI & Spatial Intelligence.
Jiawei Ren @jiawei6_ren
1K Followers 770 Following Research Scientist @NVIDIA. PhD student at @MMLabNTU.
Tri Dao @tri_dao
33K Followers 632 Following Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems.
Stephen Roller @stephenroller
5K Followers 1K Following MoTS @thinkymachines. previously pre-training @googledeepmind ,@character_ai, and @aiatmeta.
Georgia Channing @cgeorgiaw
4K Followers 229 Following AI4Science @ 🤗, PhD @OxfordTVG — science is a candle in the dark
Sangho Suh @sangho_suh
992 Followers 611 Following Research Scientist @allen_ai | Prev: @UofT @DesignLabUCSD @UWaterloo | https://t.co/o2B2DtgEIC
Woosuk Kwon @woosuk_k
6K Followers 626 Following @thinkymachines | @vllm_project | PhD-ing @Berkeley_EECS
Ziwei Liu @liuziwei7
11K Followers 1K Following Associate Professor @ NTU - Vision, Learning and Graphics.
Hieu Pham @hyhieu226
34K Followers 25 Following @openai | ex: @xai, @augmentcode, @GoogleBrain, @LTIatCMU, @Stanford, ACM ICPC, IMO🥈 Opinions are my own.
Shangchen Zhou @ShangchenZhou
1K Followers 517 Following Research Assistant Professor at NTU @MMLabNTU - Computer Vision
JunMa @JunMa_11
862 Followers 1K Following Machine Learning Lead @UHNAIHUB Foundation Model for Biomedical Image Analysis https://t.co/HI26VOWGLE Opinions my own
Quanquan Gu @QuanquanGu
16K Followers 2K Following Professor @UCLA, Pretraining and Scaling at ByteDance Seed | Recent work: Build AGI | Opinions are my own
Jonathan Frankle @jefrankle
20K Followers 733 Following Chief AI Scientist @databricks via MosaicML.
Roman Chernin @romanchernin
5K Followers 407 Following Co-Founder at Nebius. We are building the best AI-centric cloud.
Balbino Yagüe Jimén... @balbinoyj
138 Followers 300 Following Granada preclinical magnetic resonance imaging (MRI) technologist in theranostics, neuroscience, cancer and cardiovascular diseases 🐭 🧠🫀🩻.
Oxford Torr Vision Gr... @OxfordTVG
2K Followers 86 Following TVG @UniofOxford; Computer Vision, Machine Learning and latest research for Artificial Intelligence.
Muyu He @HeMuyu0327
970 Followers 224 Following Post-training @CollinearAI | Trying to be an expert of mixtures
André Terron @Andre_Terron
1K Followers 936 Following coding interfaces, AI and quantified self. SDK engineer @statsig (acquired by @OpenAI) prev @Microsoft, @ValDotTown
Yue Wu @FrankYueWu1
2K Followers 515 Following Scaling RL @xAI | Prev. Postdoc @Princeton, CS PhD @UCLA. BSc @PKU1898.
Sukjun (June) Hwang @sukjun_hwang
3K Followers 307 Following ML PhD student @mldcmu advised by @_albertgu
La Pausa @lapausa_fc
8K Followers 697 Following An analytical look at La Liga and 🇪🇸 football, by @robbiejdunne & @jamiemkemp. Subscribe to our Substack below:
Fernando 🇮🇹🇨... @Franc0Fernand0
46K Followers 236 Following Dad and husband • Software Engineer for 15+ years • Algorithms, Distributed Systems, System Design, Computer Vision