Soham De @sohamde_
Research Scientist at DeepMind. Previously PhD at the University of Maryland. sohamde.github.io London, England Joined May 2011-
Tweets190
-
Followers2K
-
Following1K
-
Likes801
The Training team @OpenAI is hiring researchers in London 🚀 Our twin missions are to train better LLMs, and serve them more cheaply Get in touch if you are excited to collaborate on architecture design, reliable scaling, and faster optimization
Excited to share #AlphaGenome, a start of our AlphaGenome named journey to decipher the regulatory genome! The model matches or exceeds top-performing external models on 24 out of 26 variant evaluations, across a wide range of biological modalities.1/6
We have a new SSM theory paper, just accepted to COLT, revisiting recall properties of linear RNNs. It's surprising how much one can delve into, and how beautiful it can become. With (and only thanks to) the amazing Alexandre and @BachFrancis arxiv.org/pdf/2502.09287
📢 New paper on creativity & multi-token prediction! We design minimal open-ended tasks to argue: → LLMs are limited in creativity since they learn to predict the next token → creativity can be improved via multi-token learning & injecting noise ("seed-conditioning" 🌱) 1/ 🧵
Excited to share what my team has been working on lately - Gemini diffusion! We bring diffusion to language modeling, yielding more power and blazing speeds! 🚀🚀🚀 Gemini diffusion is especially strong at coding. In this example the model generates at 2000 tokens/sec, including overheads like tokenization, prefill, safety filters etc.
We’ve developed Gemini Diffusion: our state-of-the-art text diffusion model. Instead of predicting text directly, it learns to generate outputs by refining noise, step-by-step. This helps it excel at coding and math, where it can iterate over solutions quickly. #GoogleIO
Excited to share that our paper "Bridging the human–AI knowledge gap through concept discovery and transfer in AlphaZero" is now out in PNAS! With @weballergy, @banburismus_, @demishassabis, @ulrichpaquet, @_beenkim 🎉 📄 doi.org/10.1073/pnas.2…
Our new paper sheds light on the process of knowledge acquisition in language models, with implications for - data curricula - the challenges of learning new knowledge when fine-tuning - the emergence of hallucinations. Nicolas did a great job on the project! See his thread👇
Large language models store vast amounts of knowledge, but how exactly do they learn it? Excited to share my @GoogleDeepMind internship results, which reveal the fascinating dynamics behind factual knowledge acquisition in LLMs! arxiv.org/abs/2503.21676
Today, we’re open-sourcing our SynthID text watermarking tool through an updated Responsible Generative AI Toolkit. Available freely to developers and businesses, it will help them identify their AI-generated content. 🔍 Find out more → goo.gle/40apGQh
Great contribution from Meta to the research community with a very easy-to-read codebase for LLM development: github.com/facebookresear… @sohamde_ and @SamuelMLSmith have implemented Hawk as well, which seems to have a performance comparable to Mamba.
We have an opening for a PhD intern working closely with (among others) me, Arwen Bradley, David Berthelot, on scientific aspects of diffusion & generative models. 1/
We’re presenting AlphaProteo: an AI system for designing novel proteins that bind more successfully to target molecules. 🧬 It could help scientists better understand how biological systems function, save time in research, advance drug design and more. 🧵 dpmd.ai/3XuMqbX
@champydaku The data efficiency comes primarily due to better tuning. We did a lot of work to establish hyperparameter scaling rules for Griffin so we can scale efficiently - we might write this up at some point. We compare diff capabilities in the Griffin paper: arxiv.org/abs/2402.19427
Two months back, we released a 9B RecurrentGemma model, one of the strongest SSM-based language models out there, trained on 2T tokens! I finally updated arXiv with some of our results: arxiv.org/abs/2404.07839 Link to weights and code for our models in thread!
A new blog post talking about Gemma architecture explained! This time is RecurrentGemma: developers.googleblog.com/en/gemma-expla… This is the Gemma model that is not based in the Transformers architecture but on Recurrent Neural Network! Is this the return of RNNs? #gemmaverse
Both pre-trained and instruction-tuned models are here: huggingface.co/google/recurre… huggingface.co/google/recurre… Code here: github.com/google-deepmin… And ofc, we have our 2B version of RecurrentGemma as well, released earlier this year! huggingface.co/google/recurre… huggingface.co/google/recurre…
Are small models still undertrained? We are releasing a 2B model that beats GPT-3.5. The crazy part is that it was distill on only 2T tokens from a small model. Distillation is the future of LLMs with the growing availability of large and efficient open models!
It was fun to moderate this discussion with a great group of panelists. Lots of interesting points made on how to approach the next gen of seq modelling architectures. Thanks for the invite @caglarml @orvieto_antonio Razvan and others!
The panel discussion at NGSM workshop going on full steam ahead with a great line of panelists moderated by @sohamde_ ...
I am absolutely thrilled to announce the release of Gemma 2! Today, we're releasing both pre-trained-only and fully post-trained 9B and 27B models. The full technical report is here: goo.gle/gemma2report and it's live *right now* on aistudio.google.com.
Welcome RecurrentGemma 9B 🔥 > Same performance as Gemma with more than 25% lower latency and 6-7x higher tokens/ sec ⚡ > Base (9B) and Instruct (9B-IT) models released. > MMLU - 60.5, CommonSenseQA 73.2, AGIEval 39.3 - pretty strong base model to fine-tune further. > Based on the Griffin Architecture > Achieves faster inference with long sequences by replacing gloabal attention with local and linear recurrences. > Available in Transformers! 🤗 Massive Kudos to Google for continue open research for alternative architectures! GG!
AK @_akhaliq
512K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo ,submit papers here: https://t.co/UzmYN5XOCi
Lucas Beyer (bl16) @giffmana
144K Followers 619 Following Researcher (now: Meta. ex: OpenAI, DeepMind, Brain, RWTH Aachen), Gamer, Hacker, Belgian. Anon feedback: https://t.co/xe2XUqkKit ✗DMs → email
Google DeepMind @GoogleDeepMind
1.5M Followers 277 Following The engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us: https://t.co/jUHQA27iBL
Sebastian Raschka @rasbt
481K Followers 1K Following ML/AI research engineer. Ex stats professor. Author of "Build a Large Language Model From Scratch" (https://t.co/O8LAAMRzzW) & reasoning (https://t.co/5TueQKx2Fk)
Sander Dieleman @sedielem
69K Followers 2K Following Research Scientist at Google DeepMind (WaveNet, Nano Banana, Gemini Omni). I tweet about ML, music, generative models (personal account).
Tom Goldstein @tomgoldsteincs
28K Followers 2K Following Professor at UMD. AI security & privacy, algorithmic bias, foundations of ML. Follow me for commentary on state-of-the-art AI.
rohan anil @_arohan_
44K Followers 2K Following member of technical staff & co-founder of @coreautoai - and continuing to aspire to understand deep learning.
Behnam Neyshabur @bneyshabur
44K Followers 1K Following Co-Founder & CEO @mirendil 💼 Past: co-led Discovery team @AnthropicAI & Blueshift team @GoogleDeepMind 🎒Traveling & Backpacking
Jeremy Howard @jeremyphoward
323K Followers 7K Following 🇦🇺 Co-founder: @AnswerDotAI/@FastDotAI ; Prev: Professor@UQ; @kaggle founding president; founder @fastmail/@enlitic/… https://t.co/16UBFTX7mo
Jeremy Cohen @deepcohen
6K Followers 1K Following Research fellow at Flatiron Institute, working on understanding optimization in deep learning. Previously: PhD in machine learning at Carnegie Mellon.
Jeff Dean @JeffDean
449K Followers 6K Following Chief Scientist, Google DeepMind & Google Research. Gemini Lead. Opinions stated here are my own, not those of Google. TensorFlow, MapReduce, Bigtable, ...
Nathan Benaich @nathanbenaich
71K Followers 36K Following solo member of superinvestment staff @airstreet @airstreetpress @stateofai @raais
Gowthami @gowthami_s
11K Followers 984 Following Post-training @theworldlabs | SGD-ing on life | Rants, Memes my own.
Sara Hooker @sarahookr
63K Followers 11K Following Building intelligence that evolves @adaption_ai. Built @Cohere_Labs, @GoogleBrain, @GoogleDeepmind. ML Efficiency, Multimodal\lingual.
MIT CSAIL @MIT_CSAIL
347K Followers 20K Following MIT's Computer Science & Artificial Intelligence Laboratory (CSAIL). Media Inquiries: [email protected] Check out the latest CSAIL content ⬇️
Albert Catalán Tatje... @actatjer
80 Followers 743 Following ML efficiency PhD @ELLISInst_Tue & @MPI_IS before @uni_tue & @unibarcelona
AIcontributors @aicontributors
12 Followers 2K Following
Myron DSouza @myrondza10
1 Followers 250 Following Data Scientist @ Emirates NBD | FX - Strategy & Customer Intelligence | RBWM | ML + AI 🧠✨🦾
Raila @raila_san
419 Followers 2K Following ML at Google, CS at IITB. Women in Frontier AI (Twitter is for learning in public & my weird side)
Parshin Shojaee @ParshinShojaee
3K Followers 1K Following PhD student @VT_CS | understanding how LLMs reason and adapt to novel scenarios | prev Intern @Apple @Adobe | opinions are my own
na @naltmann
39 Followers 387 Following
Xiangming Gu @gu_xiangming
2K Followers 526 Following RS on LLMs. Prev: SR @GoogleDeepmind, Ph.D. @NUSingapore, B.E. @Tsinghua_Uni.
doodle @doodlext25
0 Followers 35 Following
Pratyay Banerjee (ন... @Neilblaze007
238 Followers 7K Following I live in the shadows, but I watch everything.
Behzad @bg01shan
835 Followers 1K Following MTS @OpenAI ‖ ex GenAI @GoogleDeepMind ‖ 🎶-theory enthusiast ‖ 🏃 runner with a bad knee! Opinions are *not* my own. I've heard them somewhere.
Yaru Qian @EmilyQian1024
0 Followers 30 Following
xunya @xunya78752
0 Followers 84 Following
Mnking @mnking01
0 Followers 245 Following
Maryam @Sci_Tech_Eng
88 Followers 7K Following Exploring in neural networks from inside purely biological mind with heavy cognition architecture & mapping the phase space where thought becomes destiny.
Zhengyang Qi @qi_zhengyang
861 Followers 5K Following Research @SnorkelAI | Previously: @Scale_AI Multiturn RL, reward modeling, interactive environments, artificial social intelligence
Vera Milovanović @nevera_m
113 Followers 727 Following I like doing research (on adaptive models and ML for science). PhD student at @ELLISInst_Tue, @MPI_IS and @ETH_en. | Prev. @uni_tue (MSc), @ETF_Beograd (BSc)
Miri Zilka @MiriZilka
1K Followers 410 Following Assistant Professor in Responsible Machine Learning at @CambridgeMLG and @LeverhulmeCFI.
Elliott / Shangzhe Wu @elliottszwu
10K Followers 974 Following Assistant Professor @Cambridge_Eng, working on 3D computer vision and inverse graphics, previously postdoc @StanfordSVL, PhD @Oxford_VGG
google review @pandas3020
21 Followers 3K Following
Jonathan Lorraine @jonLorraine9
7K Followers 7K Following Research scientist @NVIDIA Spatial Intelligence Lab
Nathan @arcane_bloom
696 Followers 3K Following • AI + ML @blingcapital funded startup • UG @iitmadras • I try to log about my AI/ML/Software upskillings @senthil_twt
Amanda Bertsch @abertsch72
2K Followers 925 Following PhD student @LTIatCMU / @SCSatCMU / student researcher @allen_ai, researching long context + decoding | she/her | @ abertsch on bsky or by email (https://t.co/bsHqwIM80d)
Adam Astro @AdamAstro3
1K Followers 552 Following Obsessed with graphene and the materials science revolution. Ai transformation leader.
Swapnanil Mukherjee @swapnanil_12
16 Followers 202 Following Research Fellow @MSFTResearch India | Multimodal learning and Reasoning | @AshokaUniv 26
𝑪𝒉𝒂𝒊𝒕�... @ChaitanyaJainX
317 Followers 7K Following QuantumAIMLRL DistinguishedResearchScientist, DistinguishedResearchEngineer & DistinguishedResearchPhysicist https://t.co/swNKVA1NYA https://t.co/53sy32kjA4
Dylan Foster 🐢 @canondetortugas
4K Followers 2K Following Foundations of RL/AI @MSFTResearch. Previously @MIT @Cornell_CS RL Theory Lecture Notes: https://t.co/bhgL3aLg9y
Pierfrancesco Beneven... @PierBeneventano
1K Followers 2K Following Postdoc at @MIT | ex PhD student @Princeton | Thinking of how to frame theoretically agents and using agents for theory research, while brewing my espresso.
Shiwei Liu @Shiwei_Liu66
2K Followers 602 Following Hi, I am a PI at ELLIS Institute Tübingen and MPI-IS. Was RS NIF @UniofOxford, JRF @SomervilleOx, postdoc @UTAustin, and PhD @Data_AI_TUe.
NextAI London | Axiom @nextai_london
9K Followers 8K Following Where talent collides with technology and art in London // Brought to you by Axiom // Join over +10K fans and members across all social media
Sanchayan Banerjee @snoopy_albert
66 Followers 3K Following
Avantika @a_avantika09
3 Followers 138 Following ML Researcher @RadiantLogic | Building interpretable speech AI for dysarthria assessment | wav2vec2 · WavLM · XLS-R | 5 papers (ISCSLP/SPECOM/SLT/TMLR)
Yann LeCun @ylecun
1.2M Followers 787 Following Professor at NYU & Executive Chairman at AMI Labs. Ex-Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.
Lucas Beyer (bl16) @giffmana
144K Followers 619 Following Researcher (now: Meta. ex: OpenAI, DeepMind, Brain, RWTH Aachen), Gamer, Hacker, Belgian. Anon feedback: https://t.co/xe2XUqkKit ✗DMs → email
Peyman Milanfar @docmilanfar
114K Followers 589 Following Distinguished Scientist at Google. National Academy of Engineering. Computational Imaging ∩ AI. Posts are personal opinions
François Chollet @fchollet
707K Followers 826 Following Co-founder @ndea. Co-founder @arcprize. Creator of Keras and ARC-AGI. Author of 'Deep Learning with Python'.
Google DeepMind @GoogleDeepMind
1.5M Followers 277 Following The engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us: https://t.co/jUHQA27iBL
Gautam Kamath @thegautamkamath
65K Followers 623 Following Assistant Prof of CS @UWaterloo, Faculty @VectorInst, Canada @CIFAR_News AI Chair. Joining @NYU_Courant Fall 2026. Co-EiC @TmlrOrg. I lead @TheSalonML.
Sebastian Raschka @rasbt
481K Followers 1K Following ML/AI research engineer. Ex stats professor. Author of "Build a Large Language Model From Scratch" (https://t.co/O8LAAMRzzW) & reasoning (https://t.co/5TueQKx2Fk)
Delip Rao e/σ @deliprao
70K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈
Soumith Chintala @soumithchintala
313K Followers 1K Following Building new things @thinkymachines. Also dabble in robotics at NYU. Cofounded @PyTorch. AI is delicious when it is accessible and open-source.
Sander Dieleman @sedielem
69K Followers 2K Following Research Scientist at Google DeepMind (WaveNet, Nano Banana, Gemini Omni). I tweet about ML, music, generative models (personal account).
Tom Goldstein @tomgoldsteincs
28K Followers 2K Following Professor at UMD. AI security & privacy, algorithmic bias, foundations of ML. Follow me for commentary on state-of-the-art AI.
(((ل()(ل() 'yoav)))... @yoavgo
85K Followers 2K Following
Aran Komatsuzaki @arankomatsuzaki
184K Followers 391 Following Sharing AI research. Early work on AI (GPT-J, scaling, MoE). Ex ML PhD (GT) & Google.
Dan Roy @roydanroy
67K Followers 2K Following @Google DeepMind. On leave, Canada CIFAR AI Chair and Former Research Director, @VectorInst. Professor, @UofT (Statistics/CS). Views are my own.
Rosanne Liu @savvyRL
54K Followers 1K Following Mom. Cofounded & running @ml_collective. Co-host of Deep Learning Classics & Trends. Research at Google DeepMind. DEI/DIA Chair of ICLR & NeurIPS.
Horace He @cHHillee
52K Followers 601 Following @thinkymachines Formerly @PyTorch "My learning style is Horace twitter threads" - @typedfemale
Larry Lv @larrylv
3K Followers 334 Following Post-Training @OpenAI. Training GPT-5.x Thinking models. // If I blocked you, blame my bot.
Laura Modiano @LauraModiano
9K Followers 773 Following Founder Experience @OpenAI Building for Builders
Ronnie Chatterji @RonnieChatterji
7K Followers 648 Following Chief Economist @OpenAI & Distinguished Professor @DukeFuqua. Views my own.
John Jumper @JohnJumperSci
32K Followers 0 Following
🇺🇦 Dzmitry Bahd... @DBahdanau
11K Followers 41 Following Team member at @periodiclabs. Adjunct Prof @ McGill. Member of Mila, Quebec AI Institute. Stream of consciousness is my own.
Niloofar ✈️ icml @niloofar_mire
11K Followers 2K Following Technical staff @humansand, incoming asst. prof @LTIatCMU @CMU_EPP, ex RS in @AIatMeta, postdoc @uwcse, Ph.D. @ucsd_cse, former @MSFTResearch -Privacy, ML, NLP
Joanne Jang @joannejang
51K Followers 1K Following trying to automate my work @coreautoai // prev: model behavior & labs @openai
Alexander Whedon @alex_whedon
25K Followers 65 Following Building better algorithms. Co-Founder at @subquadratic
Sam Mathverse @Sam_Axiom
35K Followers 16K Following Physics| Mathematic| |Science 🔭| | English| | Memes | |Original X Content Creator|
Atli Kosson @AtliKosson
478 Followers 539 Following ML Researcher (PhD, EPFL) — optimization & training dynamics of large neural networks | previously at Tesla, Cerebras, Amazon
Matthew Botvinick @mattbotvinick
4K Followers 115 Following Leading work on AI and Rule of Law @AnthropicAI Senior Fellow @YaleLawSch 𝘈𝘐 & 𝘗𝘰𝘭𝘪𝘵𝘪𝘤𝘢𝘭 𝘍𝘳𝘦𝘦𝘥𝘰𝘮, forthcoming @PrincetonUPress
Parshin Shojaee @ParshinShojaee
3K Followers 1K Following PhD student @VT_CS | understanding how LLMs reason and adapt to novel scenarios | prev Intern @Apple @Adobe | opinions are my own
Muyu He @HeMuyu0327
3K Followers 312 Following RL @ZyphraAI | Expert of mixtures, or 21st century schizoid man.
Subham Sahoo @ssahoo_
4K Followers 82 Following Pioneering Diffusion LLMs | Team Lead @mbzuai - IFM | PhD @cornell
Aristotelis Economide... @aristotelis_eco
857 Followers 163 Following Building autonomous systems @DeepMind
Samuel Albanie 🇬�... @SamuelAlbanie
8K Followers 1K Following gemini evals & post-training @GoogleDeepMind
Kevin Patrick Murphy @sirbayes
72K Followers 724 Following Research Scientist at Google DeepMind. Interested in Bayesian Machine Learning.
Francesco Cagnetta @Fraccagnetta
512 Followers 510 Following Theoretical physicist (bow tie included), inherently out of equilibrium. Studying data structure and deep learning. Marie Skłodowska-Curie fellow at @SISSA.
Soon @soontechnology
25K Followers 81 Following A portal into the machines, minds, and subcultures of tech's new frontier.
Alan Karthikesalingam @alan_karthi
7K Followers 2K Following Director/Principal Scientist @GoogleDeepMind. AI Co-Clinician, AI Co-Scientist, AMIE, Med-Gemini, MedPaLM Hon Lecturer Vasc Surgery @ImperialVasc
Ekin Dogus Cubuk @ekindogus
9K Followers 488 Following Co-Founder of @periodiclabs Past: Lead of materials science and chemistry at @GoogleDeepMind; Google Brain
Daria Soboleva @dmsobol
2K Followers 697 Following Scaling the world's largest MoE models @Cerebras | Creator of The MoE 101 Guide & SlimPajama | Ex-@Google @Yandex. Tweets are my own views.
Behrooz Ghorbani @_ghorbani
2K Followers 637 Following Leading Reinforcement Learning at @Reflection_ai. Scaling RL for frontier reasoning models. Formerly @OpenAI, @GoogleBrain and @stanford_ee.
Azalia Mirhoseini @Azaliamirh
19K Followers 620 Following Founder @RicursiveAI, Asst. Prof. of CS at Stanford. Prev: DeepMind, Anthropic, Brain. Co-Creator of MoEs, AlphaChip, Test Time Scaling.
Mariya I. Vasileva @mariyaivasileva
21K Followers 2K Following Research Scientist. Multimodal world models, evaluation • prev safety @Meta MSL, @AWS • 🎓 UIUC (PhD), @Caltech • @WiMLWorkshop, @CVFADworkshop • 🇧🇬
Geoffrey Irving @geoffreyirving
13K Followers 353 Following Cofounder and Chief Scientist at Resolution. Alignment will be solved, but not necessarily in time. Previously AISI, DeepMind, OpenAI, Google Brain, etc.
clare ❤️🔥 @clarejtbirch
7K Followers 1K Following thinking, doing @thinkymachines / fear is the mind-killer, solvitur ambulando
Guillaume Hennequin @GJEHennequin
638 Followers 216 Following
Adrian Weller @adrian_weller
4K Followers 3K Following Director of Research in Machine Learning at the University of Cambridge, Head of Safe and Ethical AI at The Alan Turing Institute, MBE
Scott Linderman @scott_linderman
6K Followers 934 Following Professor @Stanford Statistics and @StanfordBrain. Co-Founder of @EngramLab. AI, Neuroscience, Statistics. Posts are my own.
Miri Zilka @MiriZilka
1K Followers 410 Following Assistant Professor in Responsible Machine Learning at @CambridgeMLG and @LeverhulmeCFI.
Zoubin Ghahramani @ZoubinGhahrama1
35K Followers 714 Following VP Research, Google DeepMind, ex-head of Google Brain. Professor at University of Cambridge. Machine Learning Researcher. ex-Chief Scientist & VP of AI, Uber.
Jose Miguel Hernánde... @jmhernandez233
5K Followers 137 Following Professor of Machine Learning, University of Cambridge, UK.
Elliott / Shangzhe Wu @elliottszwu
10K Followers 974 Following Assistant Professor @Cambridge_Eng, working on 3D computer vision and inverse graphics, previously postdoc @StanfordSVL, PhD @Oxford_VGG
Tony Zhao @tonyzzhao
100K Followers 983 Following Co-founder and CEO @sundayrobotics. Stanford PhD dropout, ex Deepmind, Tesla, GoogleX
Phillip Lippe @ICML 2... @phillip_lippe
3K Followers 535 Following Research Scientist @GoogleDeepMind, RL/Multimodal/🍌 Gemini | Prev @UvA_Amsterdam - Opinions my own
Andy Masley @AndyMasley
16K Followers 2K Following When the going gets weird the weird turn pro. Researching and writing AI and other topics from a broadly EA perspective. On a grant from CG.
Trends for United States
You might like
