Ricardo Dominguez-Olmedo @rdolmedo_
PhD student at the Max Planck Institute for Intelligent Systems, working with Moritz Hardt and Bernhard Schölkopf. ricardodominguez.github.io Tübingen, Germany Joined January 2014-
Tweets99
-
Followers471
-
Following301
-
Likes209
Ricardo Dominguez-Olmedo retweeted
We (Moritz Hardt, @walesalaudeen96,@joavanschoren) are organizing the Workshop on the Science of Benchmarking & Evaluating AI @EurIPSConf 2025 in Copenhagen! 📢 Call for Posters: rb.gy/kyid4f 📅 Deadline: Oct 10, 2025 (AoE) 🔗 More Info: rebrand.ly/bg931sf
1
13
46
4K
7
Download Image
My PhD advisor, Moritz Hardt, has just released the first half of his new book, The Emerging Science of Machine Learning Benchmarks. It’s freely available and highly recommended: mlbenchmarks.org
Ricardo Dominguez-Olmedo retweeted
New preprint out! 🎉🎉 How does LLM training loss translate to downstream performance? We show that pretraining data and tokenizer shape loss-to-loss scaling laws, while architecture and other factors play a surprisingly minor role! brendel-group.github.io/llm-line/ 🧵1/8
Ricardo Dominguez-Olmedo retweeted
“Aha moments” can be observed at step 0, so we should not fixate on reporting individual instances. Instead, we should seek reliable measures of internal reasoning that can be tracked throughout training. So far, response length appears to be one such (imperfect) measure.
One important caveat is that I cannot get the response length to dramatically increase as in the R1 paper.
One important caveat is that I cannot get the response length to dramatically increase as in the R1 paper. https://t.co/3VNNkpNEAR
R1-style GRPO on Llama 3.2 1B Instruct yields +10 accuracy points on GSM8K. It just works! The train data is GSM8K train. Interestingly, supervised fine-tuning yields no performance improvements, since the dataset is tiny compared to all the math reasoning data seen by Llama 3.
Ricardo Dominguez-Olmedo retweeted
Really cool paper questioning all the 'incredible' progress we've seen recently: "after fine-tuning all models on the same amount of task data, performance per pre-training compute equalizes and newer models are no better than earlier models."
Really cool paper questioning all the 'incredible' progress we've seen recently: "after fine-tuning all models on the same amount of task data, performance per pre-training compute equalizes and newer models are no better than earlier models."
Tom Sühr @tom_suhr
129 Followers 426 Following PhD Candidate @MPI_IS previously MSc, BSc CS @TUBerlin, interested in ML benchmarking, measurement theory
Eric trump (OFFICIAL ... @Eric7Trump1
475 Followers 4K Following OUT FOR THE BETTERMENT OF THE WORLD IS TIME 🕰️ FOR JUSTICE AND CHANGE ❤️ QFS https://t.co/hc6P6D4AwB
logan koepke @jlkoepke
2K Followers 3K Following research + advocacy at the intersection of AI + civil rights. senior project director @teamupturn. also here: https://t.co/Yeh3FR4hmZ
Rohini Bhattacharjya @Bhattacharjyaro
0 Followers 51 Following
Nikita Agarwal @niki__agarwal
67 Followers 838 Following
Ofir Press @OfirPress
15K Followers 7K Following I build tough benchmarks for LMs and then I get the LMs to solve them. SWE-bench & SWE-agent. Postdoc @Princeton. PhD @nlpnoah @UW.
Eric Stewart @hippy4evrr
8 Followers 64 Following
Albert Catalán Tatje... @actatjer
9 Followers 275 Following Master student @uni_tue. Research assistant @ELLISInst_Tue
Andy Timm @Andy_Timm
410 Followers 687 Following Data scientist @ Grow Progress, testing Dem ads. Usually thinking about methods for survey weighting, efficient causal inference, or scalable Bayes.
Namdar Nejad @NamdarNejad
2 Followers 368 Following
Fabio.E Zola @equant_org
259 Followers 1K Following Data Engineer @ibm 🐧 Liberal Economist @idlibertes 🕊 Tennisman 🎾 HouseDJ since 89 🙂 Chess Player ♟️ Open standards advocate ⭕ Nulla dies sine linea 🔥
Alexander Panfilov @kotekjedi_ml
217 Followers 199 Following IMPRS-IS & ELLIS PhD Student @ Tübingen Interested in Trustworthy ML, Security in ML and AI Safety.
FariborzSadeghi @FariborzSaddeqi
88 Followers 785 Following Researcher in the ECE Department at @UnivOfTehran. |#Causality|#CausalRL|#RL|#ControlTheory|
Alexandru Fartade �... @KullAxel
2K Followers 1K Following Intelligence is the ability to avoid doing work, yet getting the work done. - Linus
Yixin Lin @yixin_lin_
2K Followers 7K Following something new. prev: embodied AI @GoogleDeepMind, FAIR/@AIatMeta, Google Brain.
Matteo Farina @farinamatteoo
158 Followers 198 Following Apparently an 🇪🇺 @ELLISforEurope AI/ML PhD Student @ 🇮🇹 the University of Trento (@UniTrento) and @ 🇩🇪 the University of Tübingen (@uni_tue)
Andreas Opedal @OpedalAndreas
387 Followers 493 Following PhD student @ETH Zürich and @MPI_IS | Language, Reasoning, and Cognition
Yoram Bachrach @yorambac
3K Followers 7K Following Research Scientist at Meta (prev Google DeepMind and Microsoft Research). Working on LLM Agents and Multi-Agent Systems.
Sara Hooker @sarahookr
50K Followers 9K Following I lead @Cohere_Labs. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, ML reliability. Changing spaces where breakthroughs happen.
Camillus Edet @CamillusEd31531
2 Followers 43 Following
Yatong Chen @YatongChen
589 Followers 529 Following Research group leader @ Max Planck Institute working on theory & social aspect of CS. Previous @UCSC @GoogleDeepMind @Stanford @PKU1898
sss ll @sssll1065194
2 Followers 166 Following
Ethan Elasky @ethanelasky
96 Followers 831 Following Independent research on AI debate, control, and safety (supported by Open Philanthropy). Previous: NLP Lab @ Academia Sinica, @Cal.
Siddartha Devic @sid_devic
299 Followers 535 Following PhD student @CSatUSC, previously undergrad @UT_Dallas. Algorithmic fairness and ML theory. ☀️ https://t.co/Y6IJwRDFPE
Max Thiessen @maxthiessen_ml
448 Followers 702 Following PhD student in machine learning @tu_wien. graph learning | convexity | learning theory
Sílvia Casacuberta @SiCaPu
795 Followers 2K Following Computer Science PhD student @Stanford. Prev.: @UniofOxford with @rhodes_trust, @Harvard '23, @MPI_IS, @CSatETH, @IBMResearch. Theory CS for responsible ML
Pietro Sittoni @CasselHank
47 Followers 1K Following
Sahajpreet Singh @Phy_Shro
139 Followers 1K Following Learning to question / PhDing @wing_nus & @nuscticnus, @NUSingapore | past: @lcs2lab @IITDelhi @BHUpro @UnivOfDelhi | CompSocSci, Misinfo, Bias, LLMs
Anna Bianchi @nawiae87
164 Followers 1K Following
Brando Miranda @BrandoHablando
1K Followers 835 Following CS Ph.D. @Stanford, researching data quality, foundation models, and ML for Theorem Proving. Prev: @MIT, @MIT_CBMM, @IllinoisCS, @IBM. Opinions are mine. 🇲🇽
ineffable alias @joorosa12185462
160 Followers 8K Following
Konrad Szafer @KonradSzafer
184 Followers 881 Following Research Assistant @ ETH Zurich | Prev: Hugging Face, CMU AutonLab
Rafael Martínez Gala... @juramaga
9K Followers 670 Following Astrophysicist at @CenterForAstro and @astro_ai_cfa.
hzhang0619 @hzhang0619
3 Followers 203 Following
Chand @ChandMoham71862
42 Followers 3K Following
MarthaZangwill @2zIJR76D3E89L8
125 Followers 2K Following
Wenhao @wenhaozhan60294
0 Followers 48 Following
walker @walk_a_lot
33 Followers 500 Following Torsion in gastropods is the most fascinating question facing the natural scientist
Jakob Foerster @j_foerst
21K Followers 985 Following Assoc Prof in ML @UniofOxford @StAnnesCollege @FLAIR_Ox/ RS @MetaAI, 2x dad. Ex: (A)PM @Google, DivStrat @GS, ex intern: @GoogleDeepmind, @GoogleBrain, @OpenAI
Nishad Singhi @nishadsinghi
455 Followers 3K Following ELLIS PhD Student working on Multimodal AI @TUDarmstadt | Prev: @MPI_IS, @UCLA | Undergrad @iitdelhi
Zoe @WavingTensor
14 Followers 829 Following
Dillon Erb @dlnrb
485 Followers 948 Following building something new @ Autonomous Technologies Group — prev: CEO / co-founder @hellopaperspace (acquired by @digitalocean)
Tom Sühr @tom_suhr
129 Followers 426 Following PhD Candidate @MPI_IS previously MSc, BSc CS @TUBerlin, interested in ML benchmarking, measurement theory
Ofir Press @OfirPress
15K Followers 7K Following I build tough benchmarks for LMs and then I get the LMs to solve them. SWE-bench & SWE-agent. Postdoc @Princeton. PhD @nlpnoah @UW.
Jia Li @JiaLi52524397
2K Followers 251 Following Co-founder at Numina; former AI scienctist at Mistral AI; Co-founder & ex CSO at Cardiologs
Alexander Panfilov @kotekjedi_ml
217 Followers 199 Following IMPRS-IS & ELLIS PhD Student @ Tübingen Interested in Trustworthy ML, Security in ML and AI Safety.
Weiyang Liu @Besteuler
2K Followers 787 Following Assistant Professor @CUHKofficial. Postdoc @MPI_IS. PhD @Cambridge_Uni & @GeorgiaTech. Previous Intern @Google & @nvidia. All opinions are my own.
Andreas Opedal @OpedalAndreas
387 Followers 493 Following PhD student @ETH Zürich and @MPI_IS | Language, Reasoning, and Cognition
Sara Hooker @sarahookr
50K Followers 9K Following I lead @Cohere_Labs. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, ML reliability. Changing spaces where breakthroughs happen.
Sílvia Casacuberta @SiCaPu
795 Followers 2K Following Computer Science PhD student @Stanford. Prev.: @UniofOxford with @rhodes_trust, @Harvard '23, @MPI_IS, @CSatETH, @IBMResearch. Theory CS for responsible ML
Brando Miranda @BrandoHablando
1K Followers 835 Following CS Ph.D. @Stanford, researching data quality, foundation models, and ML for Theorem Proving. Prev: @MIT, @MIT_CBMM, @IllinoisCS, @IBM. Opinions are mine. 🇲🇽
Konrad Szafer @KonradSzafer
184 Followers 881 Following Research Assistant @ ETH Zurich | Prev: Hugging Face, CMU AutonLab
Stella Biderman @BlancheMinerva
17K Followers 812 Following Open source LLMs and interpretability research at @AiEleuther. She/her
Daniel van Strien @vanstriendaniel
4K Followers 2K Following Machine Learning Librarian @huggingface 🤗 I like datasets.
Shane Gu @shaneguML
42K Followers 2K Following Gemini Thinking, Gibberish detective, Senior Staff RS @GoogleDeepMind. 🇯🇵-born 🇨🇳🇨🇦. ex: Gemini Multilingual Posttrain Lead, GPT-4 @OpenAI (JP: @shanegJP)
Dimitris Papailiopoul... @DimitrisPapail
20K Followers 1K Following Researcher @MSFTResearch, AI Frontiers Lab; Prof @UWMadison (on leave); learning in context; thinking about reasoning; babas of Inez Lily.
Boaz Barak @boazbaraktcs
24K Followers 600 Following Computer Scientist. See also https://t.co/EXWR5k634w . @harvard @openai opinions my own.
Ion Stoica @istoica05
5K Followers 20 Following Professor at UC Berkeley, co-founder of Databricks, Anyscale, LMArena, Conviva.
Michael Luo @michaelzluo
675 Followers 219 Following Project Lead @Agentica_ | Prev. Researcher @GoogleDeepMind | PhD at UC Berkeley @berkeley_ai
Machel Reid @machelreid
3K Followers 1K Following research scientist @googledeepmind ♊️ post-training/thinking/rl
Rishabh Agarwal @agarwl_
17K Followers 799 Following Reinforcement Learner @periodiclabs. Adjunct Prof at McGill. Ex MSL Meta, DeepMind, Brain, Mila, IIT Bombay. NeurIPS Best Paper
Jonas Geiping @jonasgeiping
4K Followers 803 Following Machine Learning Research at the ELLIS Institute & Max-Planck for Intelligent Systems// Excited about fundamental questions in Safety & Efficiency of modern ML
Shashwat Goel @ShashwatGoel7
2K Followers 1K Following Scaling supervision for AI on evals that matter. 👨🍳Forecasting, Long Horizon, Synth Data for RL RS Intern @AIatMeta PhDing @ELLISInst_Tue @MPI_IS
Ameya P. @AmyPrb
400 Followers 471 Following Exploring Science of Benchmarking & Scaling up Automated 🧬 Discovery. Postdoc @bethgelab @uni_tue; Previously: @OxfordTVG, @intelailabs RT != endorsement
George @georgejrjrjr
4K Followers 1K Following writing about ml, neuro-woo, and tea. formerly: co-founder @ Vibecamp on Signal @ghw.01
Vishaal Udandarao @vishaal_urao
1K Followers 1K Following @ELLISforEurope PhD Student @bethgelab; Currently @Apple; Previously @GoogleAI @GoogleDeepMind @Cambridge_Uni @RutgersU @iiitdelhi
Seunghyun Seo @SeunghyunSEO7
3K Followers 814 Following deep learning enjoyer. from speech to llm, now exploring image space @midjourney
Teortaxes▶️ (Deep... @teortaxesTex
45K Followers 3K Following We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1
Jordan Darefsky @jordandarefsky
74 Followers 121 Following
Alex Havrilla @Dahoas1
2K Followers 546 Following Research Scientist @GoogleDeepMind. Interested in interestingness
Wenhu Chen @WenhuChen
23K Followers 674 Following AI researcher. Interested in Reasoning, Multimodal. I direct TIGER-Lab. Author of PoT, MMMU, MMLU-Pro, MAmmoTH, LongRAG, MAP-Neo, YuE, VL-Rethinker
Ankesh Anand @ankesh_anand
5K Followers 626 Following Research scientist @googledeepmind (Gemini Thinking & Post-Training), prev phd @milamontreal. RL for Gemini 2.5, IMO DeepThink, Mariner. Opinions are my own.
noahdgoodman @noahdgoodman
5K Followers 166 Following Professor of natural and artificial intelligence @Stanford. Alignment at @GoogleDeepMind. (@StanfordNLP @StanfordAILab etc)
André Cruz (on bsky�... @andcrz97
9 Followers 161 Following 🎓 PhD student at the Max Planck Institute 🔬 Interested in safe and robust AI, algorithms & society 🦋 https://t.co/CCHKnIBmaQ
Zihan Wang - on RAGEN @wzihanw
23K Followers 612 Following PhD Student @NorthwesternU. Intern @yutori_ai. I study PhysiCS of LLM. Ex @deepseek_ai @uiuc_nlp @RUC. RAGEN | Chain-of-Experts | ESFT.
Nikhil Chandak @nikhilchandak29
394 Followers 423 Following PhD Student at Max Planck Institute. Past @iiit_hyderabad @VectorInst. Interested in better evals, forecasting, and open-endedness.
Yao Fu @Francis_YAO_
20K Followers 2K Following Research Scientist at @GoogleDeepMind I study complex, multimodal, interactive reasoning. Opinions are my own
Sam Park @smsampark
435 Followers 560 Following Postdoc at Stanford CS. Previously: MIT PhD, Cornell BS
Parth Thakkar @parth007_96
2K Followers 2K Following @Meta | Previously @IllinoisCS @MSFTResearch @IBMResearch | LLMs + code
Nino Scherrer @ninoscherrer
994 Followers 2K Following Research Scientist at @Google | Rigorous evaluations, cognitive science & causality | Ex: {@PatronusAI, @VectorInst, @Mila_Quebec, @MPI_IS, @ETH_en}
Saurabh Srivastava @_saurabh
951 Followers 831 Following Building the next stage of AI @ Essential AI Previously: 2x YC (W15, S18); PhD + Postdoc in Program Synthesis
Adhiraj Ghosh ✈️ ... @adhiraj_ghosh98
260 Followers 507 Following ELLIS PhD @uni_tue | vision-language & data-centric ML @bethgelab 🦋: https://t.co/Q03vvJFIPw
Yangjun Ruan @YangjunR
1K Followers 721 Following Creating @thinkymachines | Prev @UofT @stanfordAILab @VectorInst
Andrei Nicolicioiu @anNicolicioiu
490 Followers 694 Following PhD student @Mila_Quebec, visiting researcher @AIatMeta studying robustness, reasoning, causal ML. Past @MPI_IS @Bitdefender. https://t.co/Cyy1hSkebi
Omar Khattab @lateinteraction
25K Followers 3K Following Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.
Cozmin Ududec @CUdudec
370 Followers 2K Following @AISecurityInst Testing and Science of Evals. Ex quantum foundationalist.
Charlie Snell @sea_snell
8K Followers 6K Following PhD student @berkeley_ai; research @cursor_ai; prev @GoogleDeepMind. My friend told me to tweet more. I stare at my computer a lot and make things
Trends for United States
17,3 B posts
10,9 B posts
4.517 posts
41,4 B posts
241 B posts
1.009 posts
3.706 posts
4.769 posts
12 B posts
152 B posts
10,2 B posts
1.326 posts
49 B posts
20,8 B posts
4.810 posts
91,1 B posts
24 B posts
314 B posts
5.257 posts
You might like
Patrik Reizinger
@rpatrik96
2K Followers
Krikamol (Hiring Post...
@krikamol
3K Followers
Vincent Stimper
@VStimper
1K Followers
Felix Dangel
@f_dangel
165 Followers
Karsten Roth
@confusezius
1K Followers
Celestine Mendler-Dü...
@CeleMenDu
660 Followers
Sebastian Bordt
@sbordt
292 Followers
Miriam Rateike
@miriamrateike
318 Followers
Dingling Yao
@Dingling_Yao
216 Followers
Amir-Hossein Karimi
@amirhkarimi_
2K Followers