Martin Tutek @mtutek
Postdoc @ University of Zagreb | previously postdoc @ Technion and UKP Lab, TU Darmstadt | PhD @ TakeLab, UniZG | Working on interpretability & safety of LLMs. mttk.github.io Republic of Croatia Joined October 2015-
Tweets668
-
Followers599
-
Following1K
-
Likes4K
With the large influx of submissions and a faster pace of research, reproducibility is more important than ever. With this reproducibility challenge, we want to put the focus on best practices wrt. baselines🧱, ablations🌈, eval🔎 and generalizability🗺️ of interpretability!
📣 Announcing the BlackboxNLP 2026 Reproducibility Challenge! A new track dedicated to rigorous robustness checks of NLP interpretability work - stress-testing baselines, ablations, generalizability, and evaluation.
📣 Announcing the BlackboxNLP 2026 Reproducibility Challenge! A new track dedicated to rigorous robustness checks of NLP interpretability work - stress-testing baselines, ablations, generalizability, and evaluation.
We evaluated CoT faithfulness evaluations & released 𝐁𝐨𝐧𝐚𝐅𝐢𝐝𝐞 so you can test yours too!!
Can we tell when LLMs are being unfaithful in their chains of thought? We evaluated 8 methods claiming to do this, and found that most perform near chance! But evaluating this requires us to have ground-truth labels for CoT faithfulness. How can we obtain these?
Can we tell when LLMs are being unfaithful in their chains of thought? We evaluated 8 methods claiming to do this, and found that most perform near chance! But evaluating this requires us to have ground-truth labels for CoT faithfulness. How can we obtain these?
@sahoo2vec Agreed, I was extremely (pleasantly) surprised by the quality of pretty detailed reviews. Good job @pluralistic_ai
📢📢 I'm expanding my group at the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems and hiring 3-4 PhD students, and also visiting PhD students for funded 3-6 months stays ✨💥 Research areas broadly span the safety, security, and trustworthiness of AI agents including: • Sycophancy, decision-making, and societal implications of AI • Autonomous agents and memory • Multi-agent safety, security, and privacy • Training dynamics of LLMs • AI control and oversight • AI for science I'm looking for: - Visiting PhD students with a strong computer science background and research experience. - Students with a Master's degree and demonstrated research experience. What we offer in Tübingen: amazing compute, collaborators, environment, and a lovely town! If you're interested, please fill out the Google form on my website: s-abdelnabi.github.io @ELLISInst_Tue @MPI_IS #phd #AIsafety
Can one reverse-engineer a transformer from just its behavior? We show it's provably possible for individual attention heads.
Given black-box access to a Transformer's output, can we efficiently recover its parameters? We analyse the learnability of attention-based models with query access in our new work. Accepted at #ICML2026 🎉 Work done with @shahkulin98, @mhahn29 and Varun Kanade. 🧵
NLAs are claimed to verbalize model activations. But can they faithfully interpret steered activations? In our latest paper, we show that steering moves activations into non-invertible regions; and almost surely, no prompt maps to steered activations! NLAs fail to interpret steered activation states faithfully, supporting our results! ↓ @anqi_liu33 @DanielKhashabi x.com/AnthropicAI/st…
@NitCal The best viewpoint I've seen on this. I'd even be more blunt and say that it is just disrespectful to hand over AI generated content which you have not verified. Use AI tools, but check their outputs and respect others' time.
My advisor always says time is our most valuable resource, I tell students I teach/work with that I dont plan to spend more time reading something than the author spent writing it. I support arXiv's decision. Asking authors to polish AI-generated content is a *VERY* low bar.
Attention @arxiv authors: Our Code of Conduct states that by signing your name as an author of a paper, each author takes full responsibility for all its contents, irrespective of how the contents were generated. 1/
Attention @arxiv authors: Our Code of Conduct states that by signing your name as an author of a paper, each author takes full responsibility for all its contents, irrespective of how the contents were generated. 1/
To be presented at ICML! 🇰🇷
New paper. A Positive Case for Faithfulness. When asked to explain their decisions, LLMs can give highly plausible self-explanations. But are these explanations actually faithful, or are they just post-hoc rationalizations? We measure faithfulness via simulatability.
excited to share that our paper on CoT faithfulness has been accepted to #ACL2026 main! 🎉 check out the thread for details 👇
🚨 Is Chain-of-Thought really “not explainability”? Recent papers claim CoTs are mostly unfaithful because models often fail to verbalize hints that flip their answers. In our last paper of the year w/ @shsriva, we show this conclusion is misleading. (1/10 🧵)
i ran an analysis of EU-affiliated papers at ICLR 2026. the picture is less negative than the original (quoted) treemap may suggest, but still, Europe needs to wake up. 1,059 out of 5,355 papers have at least one EU affiliation. that's a 19.78% incidence on all accepted papers. If we count each paper once for every EU country represented among its authors, the total rises to 1,230 paper-country incidences. Germany leads by a large margin, followed by France and Italy (daje). as an Italian, i'm genuinely happy to see Italy so high in the ranking, our investments in national talent is paying off. this seems to correlate with the acceptance rates in competitive funding schemes like the ERC grants. i'd be curious to know whether similar patterns also appear in other non-AI fields, happy to hear thoughts from my @yacadeuro colleagues on this. also, @EU_Commission, feel free to use the data. personally i find it great to see Poland growing so strongly; there is real talent there. Austria is also becoming increasingly visible, helped by new, forward-looking institutions. i'll rerun this analysis for ICML in a couple of months. curious to see whether the same pattern holds. edit: fixed Austria counting.
someone analyzed all 5000+ accepted papers at ICLR 2026, and it's a good signal who's pushing the research of AI: > China has surpassed the US with 43.7% of the papers > Europe's contribution is surprisingly small (5.3% including UK)
Our work has been accepted at ICML 2026!🎉 Ever wondered how an LLM's conversational past influences its future, both mechanistically and behaviorally? We found that conversational history creates a "geometric trap" in the model's latent space!
How does an LLM’s past influence its future?🤔 In our new paper with @FazlBarez,@mtutek,@boknilev, Shay Cohen, we show that conversational history creates a "geometric trap" in the latent space, confining the model’s trajectory➡️making old habits e.g. hallucinations hard to break
@gsarti_ One step closer to having a local analog LM running on an abacus
Ever wondered what pathways steering vectors work through to affect model outputs, or whether different steering methods are functionally similar? We also find that steering vectors can be sparsified *a lot*. Check out our recent preprint, led by Stephen: arxiv.org/abs/2604.08524
Excited to share my recent work on interpreting LM steering vectors! Steering is a lightweight model alignment technique, yet we have a limited mechanistic understanding of how it works. We perform a case study on refusal steering to investigate. arxiv.org/abs/2604.08524
@chengyun01 @icmlconf @AdiSimhi Ooh very interesting! will read & keep in mind for CR!
Now accepted to ICML 2026 @icmlconf #ICML! Check out our work where @AdiSimhi analyzes LLMs propensity to repeat behavior such as hallucinations, sycophancy and refusal - both behaviorally & mechanistically. I'll go to Seoul, LMK if you'll also be there!
How does an LLM’s past influence its future?🤔 In our new paper with @FazlBarez,@mtutek,@boknilev, Shay Cohen, we show that conversational history creates a "geometric trap" in the latent space, confining the model’s trajectory➡️making old habits e.g. hallucinations hard to break
Qwen first release on interpretability (qwen scope) is very interesting they use SAE features to identify what causes repetition in model outputs, then use steering to manufacture a "bad" rollout where the model repeats a lot. this gives RL a clear negative signal to learn from, since repetition barely shows up in normal rollouts so the model never gets punished for it they also use SAE features as a fingerprint for benchmarks, you look at which features each benchmark activates and compare overlap. lets you find redundancy inside a benchmark and across benchmarks without running any model. for instance 63% of GSM8K features are in MATH but only 10% the other way
Ana Marasović @anmarasovic
6K Followers 599 Following Asst prof @UUtah · Ex @allen_ai @uwnlp @HD_NLP · she/her 🇭🇷
Pasquale Minervini @PMinervini
10K Followers 5K Following Research in ML/NLP at @EdinburghNLP (tenured faculty at @EdinburghUni), Co-Founder @Miniml_AI, @ELLISforEurope Scholar, https://t.co/5dUI3EFMmW
Yonatan Belinkov @boknilev
6K Followers 1K Following Associate professor of computer science @TechnionLive; visiting scholar @KempnerInst 2025-2026.
Sam Bowman @sleepinyourhat
65K Followers 3K Following AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. Into @givingwhatwecan.
Naomi Saphra @nsaphra
11K Followers 1K Following Waiting on a robot body. All opinions are universal and held by both employers and family. Now a dedicated grok hate account. Accepting ML/NLP PhD students.
Barbara Plank @barbara_plank
9K Followers 958 Following I moved to a new sky, find me there. Account no longer active. https://t.co/wnGfbtVgZ3
Marco Guerini @m_guerini
1K Followers 1K Following Head of @LanD_FBK research group at @FBK_research | NLP for Social Good.
Ofir Press @OfirPress
18K Followers 8K Following I push the AI frontier by building tough benchmarks with amazing people. SWE-bench, SWE-agent, SciCode, AlgoTune. Postdoc @Princeton. PhD @nlpnoah @UW.
Anne Lauscher (she/he... @anne_lauscher
1K Followers 462 Following Ethical and safe AI in the era of #LLMs Full Professor of Trustworthy AI @unihh leading @TrustAI_lab Previously @MilaNLProc @dwsunima @allen_ai @grammarly
Gabriele Sarti @gsarti_
2K Followers 2K Following Open-source interpretability to seize the means of prediction. Postdoc w/ @davidbau @ndif_team @Northeastern. Prev: @GroNLP, @amazonscience
Grzegorz Chrupała �... @gchrupala
5K Followers 958 Following This account is no longer active. Find me on 🦋.
Ivan Sekulić @puding_p
413 Followers 362 Following PhD from @USI_INF. Conversational Search, IR, NLP. 🐧
Laura Ruis @LauraRuis
7K Followers 827 Following Postdoc with @jacobandreas @MIT_CSAIL. PhD from @ucl_dark with @_rockt and @egrefen. Anon feedback: https://t.co/sbebAl53tU
Sarah Wiegreffe @sarahwiegreffe
6K Followers 1K Following Research in NLP & trustworthy ML (mostly interpretability). Trying to make LMs more transparent, reliable, & safe. Assistant prof @umdcs @clipumd Views my own.
Brihi Joshi @BrihiJ
2K Followers 4K Following PhD-ing @nlp_usc🏝 + @AmazonScience @Apple Fellow, ex-@IIITDelhi. Sky pics, #NLProc, everything music and cat content, mostly thinking about personalization
Miryam de Lhoneux/ @m... @mdlhx
3K Followers 1K Following #NLProc assistant prof @CW_KULeuven, PI @lagom_nlp. I like syntax more than most people. Also multilingual NLP, interpretability, mountains and beer. (She/her)
Sebastian Gehrmann @sebgehr
6K Followers 2K Following Making AI trustworthy as Head of Responsible AI in the CTOs office @Bloomberg. Formerly LLMs @ Google Brain / PhD @ Harvard. views my own
Lucie Flek @lucie_nlp
4K Followers 4K Following #NLProc researcher, computer science prof @UniBonn Nothing new to see here in 2025. You will find my news via https://t.co/ms0AC3UfbJ #eXit
Verna Dankers @vernadankers
954 Followers 331 Following Postdoc @Mila_Quebec @McGill_NLP 🇨🇦 PhD from @Edin_CDT_NLP 🏴 memorization vs generalization x (non-)compositionality x interpretability. she/her
Steven Molotnikov @smolotnikov
268 Followers 2K Following Fellow @Cosmos_Inst. Researching human-AI collaboration + scalable oversight. Previously fusion, robots, and rockets.
Satwik Bhattamishra @satwik1729
868 Followers 816 Following CS PhD student at Oxford | Worked at Google, Cohere, and Microsoft Research
Mor Geva @megamor2
3K Followers 565 Following Assistant Professor at @TelAvivUni and Research Scientist at @Irregular; previously at @GoogleResearch, @GoogleDeepMind and @allen_ai
37 @37ruch
57 Followers 3K Following
Akhil Arora @aroraakhilcs
465 Followers 416 Following Asst Prof @csaudk / Fellow @CPH_SODAS | NLP, Agentic AI, Causality, Graph ML | Previous: CS PhD @ICepfl / RS @americanexpress @Xerox @Intel • 🥾🏔️🚴♂️🏋️♂️🎸
~🤍~ @beba_ameba
230 Followers 531 Following i shape-shift with minerals, also a mathematician interested in philosophy maybe some world records on Whoop :)
difancuk @difancuk
13 Followers 149 Following
Pretam Ray @pretam_ray
38 Followers 638 Following MS(Research) @IITKgp |Ex-Research Intern Fellow @AMD | BTech @iiest_s https://t.co/Kp5U3LDAdO
Yun Cheng @chengyun01
199 Followers 401 Following 3rd-year PhD student @PrincetonCS @PrincetonPLI. prev @mldcmu @SCSatCMU.
FARRUKH KHAN @1khanfarrukh
5K Followers 7K Following Founder & CEO Inference Analytics, building AI for sensitive data industries, AI entrepreneur. Alum: IBM (Big Data), Informatica, MicroStrategy, McKinsey.
Keivan Rezaei @RezaeiKeivan
455 Followers 348 Following CS Ph.D. Student @UofMaryland || Prv. Research Intern @Adobe || Prv. Student Researcher @GoogleAI || Prv. intern @allen_ai Ai2 || Alum @SharifSocial
Michael Rizvi-Martel @frisbeemortel
154 Followers 150 Following PhD Université de Montréal & Mila. Interpretability & DL theory
Riccardo Cadei @riccardocadeii
271 Followers 828 Following PhD student in Causal Learning and AI @ISTA | ex @Harvard @EPFL
Yuntian Deng @yuntiandeng
9K Followers 4K Following language models, world models | AP @UWaterloo | Associate @Harvard | Faculty Affiliate @VectorInst | Former Postdoc @ai2_mosaic | PhD @Harvard
Young D. Kwon ✈️ ... @YoungDKwon1
409 Followers 1K Following AI Scientist @ Samsung AI | Shipped on-device GenAI to Galaxy flagships (S24 · S25 · S26) | Visiting Scholar & PhD @ Cambridge | ML & Systems Rising Star (2025)
J Rosser @jrosseruk
768 Followers 1K Following Intern @Cohere | DPhil @UniofOxford @j_foerst | MATS 10.0 @NeelNanda5
Tanmoy Mukherjee @langer_han
1K Followers 3K Following Senior researcher.Avid reader. Interested in ML/Explainability/Interpretability/CV
Louis @Louis9687221579
73 Followers 3K Following Mainline Economics | Idea page | ramblings of a schizo
bhagyesh 🏴☠�... @invi_bhagyesh
651 Followers 7K Following maths ∩ AISafety, sophomore, I play dice, working w/ @lionellevine, currently on exchange @USTC
Zhuofan Josh Ying @zfjoshying
255 Followers 700 Following PhD student @KriegeskorteLab @Columbia. Research in comp neuro and ai safety. Fun in 🐦🎹🎭.
Xinting Huang @huangxt233
145 Followers 140 Following PhD student at Saarland University https://t.co/9nBzEDGXn2 currently working on interpretability of neural models
Michelle Anne @Michell4972
53 Followers 853 Following
Koyena Pal @kpal_koyena
371 Followers 287 Following Ph.D. Student @KhouryCollege | Data Scientist co-op @Fidelity | Interpretable AI + Data Science with @davidbau and Renée Miller | BS/MS @BrownCSDept
sirine @torchsoftmax
50 Followers 297 Following
Josh Harkins-Finn @JHarkFinn
2 Followers 8K Following
Philip Schroeder @Philip_MIT
728 Followers 696 Following PhD student at MIT in Computer Science. @MIT_CSAIL @MITEECS @nlp_mit
Farhan Ishmam @aplycaebous
19 Followers 116 Following PhDing @UUtah, trying to build AI that helps people
nrRNjkitRHmMP @RNjkit72037
0 Followers 4K Following I'm interested in category theory and machine learning.
BlackboxNLP @BlackboxNLP
798 Followers 18 Following The leading workshop on analysing and interpreting neural networks for NLP Co-located with EMNLP 2026 in Budapest, Hungary
Behzad @behzadshomali
43 Followers 212 Following Graduate Computer Science Student | Deep Learning enthusiastic
Bernardo Pamplona @Bgpamplona
1 Followers 4K Following
Chloe H. Su @Huangyu58589918
1K Followers 2K Following CS PhD @Harvard @KempnerInst| SR @GoogleDeepMind | Prev Automated Reasoning @AmazonScience @mldcmu @ntusg
Ralphael Lundt @RLundt20993
48 Followers 6K Following
ALI FADHEL @ALIFADH51815460
122 Followers 1K Following
Art is life @Artislife517451
52 Followers 2K Following
Gal Pomerants (Kesten... @KestenGal
52 Followers 109 Following Masters student at Technion, Interpretability research
Anisha Saha @anishashhh
25 Followers 326 Following ELLIS PhD student at MPI-Informatics and The University of Edinburgh
Fazeela Mughal @FazeelaMug276
10 Followers 76 Following Researcher💻| AI Tools & Tech Enthusiast🧠| No-Code Explorer 🚀| Admiring AI Innovation & Sharing Insights👾| Branding & Ad Generation💡| DM for Collaboration🤝
Nandan Thakur @beirmug
3K Followers 3K Following PhD @uwaterloo • (prev) intern @DbrxMosaicAI @GoogleAI, RA @UKPLab • IR+NLP research (https://t.co/kxQprYr7Xn, https://t.co/YVvVjSyXOS, TREC-RAG and FreshStack)
Tanise Ceron @taniseceron
253 Followers 405 Following Postdoc @MilaNLProc | Interested in language models and how they shape the information environment
Zena Al-Khalili @KhaliliZena
19 Followers 102 Following PhD candidate @LstSaar and @SIC_Saar Associated with @neuroexplicit
Mayank @n0t_mayank
233 Followers 1K Following Wandering around for tweets and papers. Opinions are my own. @ELLISforEurope #NLProc also https://t.co/0PV1Y3kWmx
Aleksandra Bakalova @abakalova13175
122 Followers 162 Following (also go by Sasha) PhD student https://t.co/cO2r86TIPj
(((ل()(ل() 'yoav)))... @yoavgo
82K Followers 2K Following
François Chollet @fchollet
693K Followers 826 Following Co-founder @ndea. Co-founder @arcprize. Creator of Keras and ARC-AGI. Author of 'Deep Learning with Python'.
Ana Marasović @anmarasovic
6K Followers 599 Following Asst prof @UUtah · Ex @allen_ai @uwnlp @HD_NLP · she/her 🇭🇷
Pasquale Minervini @PMinervini
10K Followers 5K Following Research in ML/NLP at @EdinburghNLP (tenured faculty at @EdinburghUni), Co-Founder @Miniml_AI, @ELLISforEurope Scholar, https://t.co/5dUI3EFMmW
Kyunghyun Cho @kchonyc
86K Followers 2K Following a mediocre combination of a mediocre scientist and a mediocre advisor at @nyuniversity (@CILVRatNYU)
AK @_akhaliq
503K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo ,submit papers here: https://t.co/UzmYN5XOCi
Yonatan Belinkov @boknilev
6K Followers 1K Following Associate professor of computer science @TechnionLive; visiting scholar @KempnerInst 2025-2026.
Leon Derczynski ⚒�... @LeonDerczynski
6K Followers 1K Following NLP/ML/language/security. Principal research scientist @NVIDIA, & Prof @ITUkbh. Views ostensibly professional. llmsec stan acct
Luca Soldaini 🎀 @soldni
13K Followers 1K Following data mines are my passion ⛏️ mts @MicrosoftAI / ex co-lead Olmo @allen_ai / pfp @YanhongLi2062 / thoughts are mine, leave my employer alone / 🌈
Sam Bowman @sleepinyourhat
65K Followers 3K Following AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. Into @givingwhatwecan.
Naomi Saphra @nsaphra
11K Followers 1K Following Waiting on a robot body. All opinions are universal and held by both employers and family. Now a dedicated grok hate account. Accepting ML/NLP PhD students.
Percy Liang @percyliang
106K Followers 426 Following professor of computer science @Stanford @stanfordnlp, co-founder of @togethercompute, creator of https://t.co/7R5THVogW2, co-founder of @simile_ai, pianist
Barbara Plank @barbara_plank
9K Followers 958 Following I moved to a new sky, find me there. Account no longer active. https://t.co/wnGfbtVgZ3
Felix Hill @FelixHill84
12K Followers 740 Following Research Scientist, Deepmind I try to think hard about everything I tweet, esp on 90s football and 80s music None of my opinions are really someone else's
Sebastian Raschka @rasbt
460K 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)
@emilymbender.bsky.so... @emilymbender
56K Followers 2K Following Prof, Linguistics, UW // Faculty Director, CLMS // she/her // @[email protected] & bsky // rep by @ianbonaparte
Aran Komatsuzaki @arankomatsuzaki
178K Followers 362 Following Sharing AI research. Early work on AI (GPT-J, LAION, scaling, MoE). Ex ML PhD (GT) & Google.
Sebastian Riedel (@ri... @riedelcastro
16K Followers 456 Following Researcher in NLP/ML @deepmind, @ucl_nlp, @[email protected] on Mastodon
Santiago Aranguri @santiaranguri
788 Followers 133 Following Research Scientist at Goodfire. PhD student (math/ML theory) at NYU on leave.
Thomas Möllenhoff @tmoellenhoff
971 Followers 655 Following Senior Research Scientist (tenured) @RIKEN_AIP // Deputy Team Director of the Adaptive Bayesian Intelligence Team // PhD from @TU_Muenchen @tumcvg
John Schulman @johnschulman2
75K Followers 2K Following Recently started @thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music
Tuhin Chakrabarty @TuhinChakr
4K Followers 582 Following Assistant Prof @sbucompsc @stonybrooku Visiting Prof → @SFResearch Interests : AI, Culture and Copyright Law Formerly @ColumbiaCompSci
Jiacheng Liu @liujc1998
3K Followers 245 Following 🎓 PhD'ing @uwcse @uwnlp. 🛩 Private pilot. Prev: @allen_ai @AIatMeta @oculus @IllinoisCS. 📖 🥾 🚴♂️ 🎵 ♠️
Nathan Lambert @natolambert
88K Followers 901 Following Open model research @ something new. Prev. co-led Olmo at Ai2. Contact via email. Writes @interconnectsai Wrote The RLHF Book, 🏔️🏃♂️
Shayne Longpre @ShayneRedford
6K Followers 1K Following Lead the Data Provenance Initiative. PhD @MIT. 🇨🇦 Prev: @Google Brain, Apple, Stanford. AI/ML/NLP
Gabriele Berton @gabriberton
15K Followers 1K Following Training VLMs at @GoogleDeepMind - ex @Amazon @CarnegieMellon @PoliTOnews @IITalk - I post honest non-AI-generated paper reviews
Pluralistic Alignment... @pluralistic_ai
307 Followers 14 Following Pluralistic Alignment Workshop at ICML2026
Sukrati Gautam @Sukratiii
134 Followers 1K Following AI Safety | PhD @Purdue | Applied Scientist @Amazon Science | Prev @Bayer @Microsoft | Btech @IITDelhi
Julian Minder @jkminder
793 Followers 601 Following PhD at EPFL with Robert West and Ryan Cotterell, MATS 7 Scholar with Neel Nanda
Satwik Bhattamishra @satwik1729
868 Followers 816 Following CS PhD student at Oxford | Worked at Google, Cohere, and Microsoft Research
Jiaxin Wen @jiaxinwen22
6K Followers 192 Following research @berkeley_ai @anthropicai. prev @tsinghua_univ.
Andrew Lee @a_jy_l
1K Followers 1K Following postdoc-ing at harvard, phd-ed at UMich. Interested in model interpretability
Ryan Greenblatt @RyanPGreenblatt
9K Followers 6 Following Chief scientist at Redwood Research (@redwood_ai), focused on technical AI safety research to reduce risks from rogue AIs
Akhil Arora @aroraakhilcs
465 Followers 416 Following Asst Prof @csaudk / Fellow @CPH_SODAS | NLP, Agentic AI, Causality, Graph ML | Previous: CS PhD @ICepfl / RS @americanexpress @Xerox @Intel • 🥾🏔️🚴♂️🏋️♂️🎸
Or Litany ✈️ CVPR @orlitany
3K Followers 813 Following Assistant professor @TechnionLive and Sr. Research Scientist @NVIDIA | I think therefore AI
Zhuokai Zhao @zhuokaiz
5K Followers 341 Following AI Research Scientist @Meta. Building scalable intelligence. PhD @UChicagoCS.
Lee Sharkey @leedsharkey
3K Followers 2K Following Scruting matrices @ Goodfire | Previously: cofounded Apollo Research
Yun Cheng @chengyun01
199 Followers 401 Following 3rd-year PhD student @PrincetonCS @PrincetonPLI. prev @mldcmu @SCSatCMU.
NDIF @ndif_team
528 Followers 0 Following The National Deep Inference Fabric, an NSF-funded computational infrastructure to enable research on large-scale Artificial Intelligence. https://t.co/STsQ707an3
Keivan Rezaei @RezaeiKeivan
455 Followers 348 Following CS Ph.D. Student @UofMaryland || Prv. Research Intern @Adobe || Prv. Student Researcher @GoogleAI || Prv. intern @allen_ai Ai2 || Alum @SharifSocial
Filip Szatkowski @f_szatkowski
163 Followers 182 Following AI Scientist at https://t.co/zOkcUjCRzZ and PhD Candidate at WUT
Michael Rizvi-Martel @frisbeemortel
154 Followers 150 Following PhD Université de Montréal & Mila. Interpretability & DL theory
Riccardo Cadei @riccardocadeii
271 Followers 828 Following PhD student in Causal Learning and AI @ISTA | ex @Harvard @EPFL
uai2026 @UncertaintyInAI
3K Followers 37 Following Association for Uncertainty in AI. Upcoming conference: #uai2026 August 17-21 in Amsterdam, Netherlands! 🇳🇱 We’re also here: https://t.co/Ptg22I16xe
Yuntian Deng @yuntiandeng
9K Followers 4K Following language models, world models | AP @UWaterloo | Associate @Harvard | Faculty Affiliate @VectorInst | Former Postdoc @ai2_mosaic | PhD @Harvard
MATS Research @MATSprogram
4K Followers 136 Following MATS empowers researchers to advance AI alignment, transparency, and security
Young D. Kwon ✈️ ... @YoungDKwon1
409 Followers 1K Following AI Scientist @ Samsung AI | Shipped on-device GenAI to Galaxy flagships (S24 · S25 · S26) | Visiting Scholar & PhD @ Cambridge | ML & Systems Rising Star (2025)
J Rosser @jrosseruk
768 Followers 1K Following Intern @Cohere | DPhil @UniofOxford @j_foerst | MATS 10.0 @NeelNanda5
Tanmoy Mukherjee @langer_han
1K Followers 3K Following Senior researcher.Avid reader. Interested in ML/Explainability/Interpretability/CV
Faeze Ghorbanpour @FaezeGhorbanpor
124 Followers 2K Following NLP Researcher and PhD Student at @TU_Muenchen Affiliated with @MunichCenterML
Xinting Huang @huangxt233
145 Followers 140 Following PhD student at Saarland University https://t.co/9nBzEDGXn2 currently working on interpretability of neural models
Natural Language Proc... @HEI
2K Followers 5 Following New Natural Language Processing papers from https://t.co/qq1SHrGj56: natural language processing. Thank you to arXiv for use of its open access interoperability.
Andrew Lampinen @AndrewLampinen
12K Followers 2K Following Interested in cognition and artificial intelligence. MTS at @AnthropicAI. Previously @DeepMind, cognitive science @StanfordPsych. Tweets are mine.
Ben Recht @beenwrekt
34K Followers 325 Following optimization. machine learning. uc berkeley. I blog at https://t.co/fkJujOPsJb The world won't end.
Philip Schroeder @Philip_MIT
728 Followers 696 Following PhD student at MIT in Computer Science. @MIT_CSAIL @MITEECS @nlp_mit
Farhan Ishmam @aplycaebous
19 Followers 116 Following PhDing @UUtah, trying to build AI that helps people
Kempner Institute at ... @KempnerInst
4K Followers 351 Following The Kempner Institute for the Study of Natural and Artificial Intelligence at @Harvard University. RTs ≠ Endorsements
Aruna S @arunasank
363 Followers 752 Following Curious about model cognition! EECS PhD student @MIT_CSAIL Past @medialab @hotosm @outreachy
Chloe H. Su @Huangyu58589918
1K Followers 2K Following CS PhD @Harvard @KempnerInst| SR @GoogleDeepMind | Prev Automated Reasoning @AmazonScience @mldcmu @ntusg
Kimi.ai @Kimi_Moonshot
171K Followers 136 Following Built by Moonshot AI to empower everyone to be superhuman. ⚡️API: https://t.co/mzWxjgGO1h @KimiProduct where we share cool use cases and prompts.
Gal Pomerants (Kesten... @KestenGal
52 Followers 109 Following Masters student at Technion, Interpretability research
Trends for United States
You might like
