Robert Vacareanu @robert_nlp
PhD from @UofArizona Working on #nlproc Past: 2022, 2023: Applied Scientist Intern (@AWS) Joined April 2022-
Tweets124
-
Followers251
-
Following2K
-
Likes1K
As promised, we put on Arxiv the proof we did with Gemini. arxiv.org/pdf/2505.20219 This shows that the Polyak stepsize not only will not reach the optimum, but it can cycle, when used without the knowledge of f*. Gemini failed when prompted directly ("Find an example where the…
As promised, we put on Arxiv the proof we did with Gemini. arxiv.org/pdf/2505.20219 This shows that the Polyak stepsize not only will not reach the optimum, but it can cycle, when used without the knowledge of f*. Gemini failed when prompted directly ("Find an example where the… https://t.co/PigKez4BVo
If you’re at NAACL today, I’ll be presenting this poster in Hall 3 from 2:00 – 3:30 PM. Paper link: aclanthology.org/2025.naacl-lon…
If you’re at NAACL today, I’ll be presenting this poster in Hall 3 from 2:00 – 3:30 PM. Paper link: aclanthology.org/2025.naacl-lon…
This is a turning point: I just proved a complex math result useful for my research using an LLM. I am not sure if I should be happy or scared...
Look who we found hanging out in her new @StanfordEng Gates Computer Science office! We’re truly delighted to welcome @YejinChoinka as a new @stanfordnlp faculty member, starting full-time in September. ❤️ nlp.stanford.edu/people/
Exciting that @scale_AI is sponsoring Agent Workshop at CMU in April. Students and researchers who work on agents feel free to visit CMU to present your work! I will also be traveling to Pittsburgh to share my recent focuses on agents, both capability and safety.
Exciting that @scale_AI is sponsoring Agent Workshop at CMU in April. Students and researchers who work on agents feel free to visit CMU to present your work! I will also be traveling to Pittsburgh to share my recent focuses on agents, both capability and safety. https://t.co/GBaLzLgoYj
coming to a NAACL 2025 near you! 🌞 Looking forward to discussing with folks in Albuquerque :) The camera-ready is on arxiv now, with more models, more tasks, and more compared settings-- including results comparing ICL to full finetuning! arxiv.org/abs/2405.00200
coming to a NAACL 2025 near you! 🌞 Looking forward to discussing with folks in Albuquerque :) The camera-ready is on arxiv now, with more models, more tasks, and more compared settings-- including results comparing ICL to full finetuning! arxiv.org/abs/2405.00200
Excited to share our work on RSQ — enhancing quantization by focusing on the most impactful tokens. - Rotate, Scale, Quantize: delivering strong performance - Dynamic, attention-based token importance drives better efficiency - Results across LLaMA3, Mistral, Qwen-2.5, and more
Excited to share our work on RSQ — enhancing quantization by focusing on the most impactful tokens. - Rotate, Scale, Quantize: delivering strong performance - Dynamic, attention-based token importance drives better efficiency - Results across LLaMA3, Mistral, Qwen-2.5, and more
Check out 🔥 EgoNormia: a benchmark for physical social norm understanding egonormia.org Can we really trust VLMs to make decisions that align with human norms? 👩⚖️ With EgoNormia, a 1800 ego-centric video 🥽 QA benchmark, we show that this is surprisingly challenging…
🔥 Excited to share EgoNormia! A benchmark for physical social norm understanding. Can we really trust VLMs to make decisions that align with human norms? 🌐 Check out our website for the answer: egonormia.org Proud to be part of this amazing team! 🚀
🔥 Excited to share EgoNormia! A benchmark for physical social norm understanding. Can we really trust VLMs to make decisions that align with human norms? 🌐 Check out our website for the answer: egonormia.org Proud to be part of this amazing team! 🚀
**Kindly consider sharing the post** We are seeking opinions about the current quality of reviewing in *CL conferences. We (@emnlpmeeting PCs along with @ReviewAcl EiCs) are committed to improving the review quality. We are bringing a series of changes in the review process.…
**Kindly consider sharing the post** We are seeking opinions about the current quality of reviewing in *CL conferences. We (@emnlpmeeting PCs along with @ReviewAcl EiCs) are committed to improving the review quality. We are bringing a series of changes in the review process.…
Our new paper in Findings of NAACL 2025, with Vlad Negru, @robert_nlp, @CameliaLemnaru, and Rodica Potolea, proposes a new, softer take on Natural Logic, where alignment is generated through text morphing. This yields robust performance cross domain. arxiv.org/abs/2502.09567
🧵 1/N) Excited to share our recent work at @scale_AI, "Jailbreaking to Jailbreak (J2)".😈 We present a novel LLM-as-red-teamer approach in which a human jailbreaks a refusal-trained LLM to make it willing to jailbreak itself or other LLMs. We refer to this process as…
Is your CS dept worried about what academic research should be in the age of LLMs? Hire one of my lab members! Leshem Choshen (@LChoshen), Pratyusha Sharma (@pratyusha_PS) and Ekin Akyürek (@akyurekekin) are all on the job market with unique perspectives on the future of NLP: 🧵
🚀Big update: 4 new SEAL multilingual leaderboards are LIVE — Arabic, Chinese, Japanese, and Korean! 🌍 Arabic: Gemini 1.5 Pro (gemini-exp-1121) leads the pack 🏮 Chinese: Gemini 1.5 Pro (gemini-1.5-pro-exp-0827) holds the crown 💫 Japanese & Korean: o1-preview dominates 📊 See…
SEAL Visual-Understanding Leaderboard Launch 🏆 Today, we’re introducing VISTA—a new rubric-based visual task assessment benchmark that pushes beyond simple Q&A. The leading models achieve under 40% on this eval, compared to a human baseline of ~55.4%. This highlights that…
what an amazing read: converting json to regex then regex to finite state machines, and then optimising it is brilliant!
I'm on the job market! Please reach out if you are looking to hire someone to work on - RLHF - Efficiency - MoE/Modular models - Synthetic Data - Test time compute - other phases of pre/post-training. If you are not hiring then I would appreciate a retweet! More details👇
I’m looking for a PhD intern for next year to work at the intersection of LLM-based agents and open-ended learning, part of the Llama Research Team in London. If interested please send me an email with a short paragraph with some research ideas and apply at the link below.
Come join our reading group!
@COLM_conf Done! Thanks to everyone who stopped by! Lastly, the poster + a short description of it are available here drive.google.com/drive/folders/… #COLM #COLM2024 @COLM_conf #NLP #NLProc

StephanieJoshua @5W954d0z8G43c
19 Followers 668 Following
Razvan Dumitru @RazvanDuu
12 Followers 49 Following
MirabelleYale @77skZZkOUGVFH
46 Followers 1K Following
云创兽Ai @Warmxoun624764
1 Followers 54 Following 🔍 growing girl diving deep into stock investing! seeking strategy talks. DM me for ETF flows tips! 📊 #Futures #Trading
Daryl Feeney @DarylFeene6816
93 Followers 4K Following
Alina @5L23sXh0956dGY
23 Followers 895 Following
Stone Parisian @ParisianSt88430
3 Followers 75 Following
Aurora @LeeWalter330990
6 Followers 67 Following LS Club invites friends from Europe and America, limited to 20 spots,get 3 skyrocketing stocks for free
Darkem @Darkem3027477
2 Followers 42 Following
Yslaubawm @Yslaubawm96768
92 Followers 2K Following
Shivam Singhal @ShivamSinghal56
81 Followers 106 Following AI Alignment @Meta | Prev. @scale_ai, @CHAI_Berkeley, @berkeley_ai
civil liberation for ... @thic_owens
108 Followers 2K Following
Fredrick Waters @WatersFred60492
57 Followers 3K Following
Yvluwaw @Yvluwaw63599
41 Followers 2K Following
DawnStevenson @cB7y1t86j6gG6wc
74 Followers 1K Following
Nathaniel Li @natliml
529 Followers 609 Following Preparedness @meta ai, formerly @ai_risks @scale_ai 🐻 🇺🇸
AstridDaniell @5UH2mKSI5kIrilX
70 Followers 2K Following
Darlene @darlenepruitt78
302 Followers 3K Following
Bubacarr @Bubacarr772857
216 Followers 6K Following Always take sides. Neutrality helps the oppressor, never the victim. Silence encourages the tormentor, never the tormented. #care #love #support ❤️🙏
Cristina Menghini @CriMenghini
225 Followers 704 Following happy spirit | preparedness @ MSL - prev. @scale_AI
FBK - NLP Research Gr... @fbk_nlp
53 Followers 320 Following #NLP Research Unit at @fbk_research | Site: https://t.co/CrTKHvVqzI Bluesky: https://t.co/pPzvu4l4to #FBKresearch
Mrs_Joihunt @michaeljoihunt
505 Followers 3K Following ɢᴏᴅ ғɪʀsᴛ ₿ⁱᵗᶜᵒⁱⁿ ᴛʳᵃᵈᵉʳ🌎 sᴜᴄᴄᴇssғᴜʟ ʙɪᴛᴄᴏɪɴ ᴛʀᴀᴅᴇʀ💻 ᴄʀʏᴘᴛᴏ ɪɴᴠᴇsᴛᴏʀ ᴄʀʏᴘᴛᴏ ᴍɪɴᴇʀ 100%ᴘᴀʏᴏᴜᴛ📲Glowing star ᴇxᴘᴇʀᴛ ɪɴ ʙɪɴᴀʀʏ ᴏᴘᴛɪᴏɴ ᴛʀᴀᴅɪɴɢ🎆📈📊📉💰💵💸💴💶
Milad Khademi Nori @khademinori
3K Followers 3K Following Postdoctoral Fellow, Deep Learning, @TorontoMet, PhD from @QueensU, connect with me on https://t.co/LLgovzZNBZ
Jeremy Kritz @JeremyKritz
402 Followers 2K Following AI Safety Research / Red Team @scale_ai, Mostly harmless https://t.co/KuDdeMKJrJ
DEMONX @DEMONXHARD
2 Followers 3K Following
Bill @iammilleryang
4 Followers 83 Following
Thoynair @Thoynairy2Plg
47 Followers 1K Following
Huizhuo Yuan @HuizhuoY
1K Followers 1K Following Research Scientist at ByteDance. Seed Pretraining. Ex. @UCLA @PKU
Nafise Sadat Moosavi @NafiseSadat
473 Followers 392 Following Lecturer (~Assistant Prof.) in NLP @SheffieldNLP @shefcompsci, Muslim Iranian woman إنا على العهد
Soder @Sodersqys
24 Followers 492 Following
Rytewtear @RytewtearktOXC
298 Followers 5K Following
TheFutureIsBright @HopeUnblemished
322 Followers 852 Following The future is what we will make it be. Communism is our greatest Evil. Individualism and striving are our greatest Good. Don't be evil.
Ditesorer @DitesorerYXhYD
1 Followers 113 Following
Ionut Matei @IonutMatei09
0 Followers 5 Following
Neenairth @NeenairthrXMOt
95 Followers 2K Following
linda @linda2914542024
15 Followers 332 Following
Sarikaa S @sarikaa_s3
2 Followers 197 Following
Deepak Nathani @deepaknathani11
717 Followers 947 Following PhD Student @UCSBNLP | Mentor @CAREMentorship | Prev: @AIatMeta | @AWS AI | @GoogleAI India | @IITHyderabad
T Y S S Santosh @TYSSSantosh2
252 Followers 538 Following Chair@WiNLP, SRW-AACL, Communications@ARR (24-), Amazon AGI - Speech & Audio PhD@TU Munich, CS@IITKGP; Prev Adobe, Amazon, JPMC, Microsoft
Emily Neumann @immigrationgirl
26K Followers 359 Following Immigration Attorney | Speaker | Writer | Teacher https://t.co/mUhh6bUZJu
Zephyr @zephyr_z9
32K Followers 506 Following Tech, AI, Semiconductors, Stocks, Finance. DMs are open
Olivia Simin Fan @Olivia61368522
801 Followers 985 Following 🎓Ph.D.@EPFL_en-MLO|| https://t.co/QGwaUTkuyY.@UMich. || https://t.co/QGwaUTkuyY.@sjtu1896. ML&LLM research🧐 NOT a physicist.
William Maples @WillyBone1223
96 Followers 140 Following
Jiawei Zhao @jiawzhao
3K Followers 242 Following Research Scientist at Meta FAIR @AIatMeta, PhD @Caltech, GaLore, DeepConf
typedfemale @typedfemale
39K Followers 537 Following a really exciting new account "advanced pytorch user" - @cHHillee alt: @typedalt
Ji Lin @jilin_14
6K Followers 947 Following Research @Meta Superintelligence Lab | Prev: Research @OpenAI; PhD @MIT
Tong He @simpleigth
206 Followers 222 Following Researcher @Meta MSL-TBD Lab, Reasoning/RL/LLM. Ex @GoogleDeepMind (Gemini 2.5 Pro, Co-created Deep Think, AI IMO / ICPC Gold), @Waymo Research, PhD @UCLA
Matt Deitke @mattdeitke
13K Followers 300 Following AI Researcher @ Meta Superintelligence Lab Ph.D. dropout at @uwcse
Sharad Vikram @sharadvikram
2K Followers 588 Following Researcher @ Google Deepmind. I work on JAX + Pallas (https://t.co/lPMsq3yzgL) and Gemini. In the past I worked on Oryx and TFP. I like learning.
Shuchao Bi @shuchaobi
13K Followers 692 Following Research @Meta Superintelligence Labs, RL/post-training/agents; Previously Research @OpenAI on multimodal and RL; Opinions are my own.
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
Karoline Leavitt @karolineleavitt
918K Followers 3K Following Wife. Mother. Trump White House Press Secretary. Personal account. Official White House Account: @PressSec
Karoline Leavitt @PressSec
1.6M Followers 116 Following Assistant to the President and the 36th White House Press Secretary
James Blair @JamesBlairUSA
67K Followers 2K Following White House Deputy Chief of Staff ⚡️ Trump 2024 Political Director 🇺🇸 🦟 Florida Man 🔥Personal Account
Margo Martin @MargoMartin47
274K Followers 98 Following Official White House Account—Special Assistant to the President and Communications Advisor, @realdonaldtrump 🇺🇸
Trapit Bansal @TrapitBansal
32K Followers 250 Following AI Research @Meta | Co-Creator of OpenAI o1 | Previously @OpenAI, @MSFTResearch, @GoogleAI, @facebook, @iiscbangalore, and undergrad @IITKanpur
Andrei Bursuc @abursuc
8K Followers 1K Following Research scientist @valeoai | Teaching @Polytechnique @ENS_ULM | Alumni @upb1818 @Mines_Paris @Inria @ENS_ULM | Feedback: https://t.co/MHAm0ClqFJ
Abhishek Sinha @a7b2_3
802 Followers 713 Following Multi-modal Gemini @GoogleDeepMind | Previously Perception @Waymo | MSCS @Stanford Deep learning enthusiast..ardent arsenal fan
Xiangming Gu @gu_xiangming
1K Followers 404 Following Ph.D. student @NUSingapore, student researcher @GoogleDeepmind. Prev: intern @SeaAIL, B.E. and B.S. from @Tsinghua_Uni.
Lulu Cheng Meservey @lulumeservey
115K Followers 3K Following Founder of ROSTRA. Ex-Activision and Substack. “Meservey isn’t your typical flack.” -The Information. Writing https://t.co/4xKo7wQTQo
deep Manifold @BetaTomorrow
551 Followers 797 Following mathematics Thief & Chief "through the window of differential equations, mathematics sees the light in the real world" / "通过微分方程的窗子,数学家看到现实世界的光" (Jiang Zehan)
Ludwig Schmidt @lschmidt3
6K Followers 424 Following Assistant professor at @Stanford and member of the technical staff at @AnthropicAI.
Shivam Singhal @ShivamSinghal56
81 Followers 106 Following AI Alignment @Meta | Prev. @scale_ai, @CHAI_Berkeley, @berkeley_ai
Annie Liao @AnnieLiao_2000
7K Followers 2K Following founder @buildclub_, reinventing how the world learns AI | sf and dating memes
ℜ𝔞𝔢 @dystopiangf
23K Followers 657 Following matrix multiplier • 4am yearner • brutalism enjoyer // redacted posts @eutopiangf
Durk Kingma @dpkingma
50K Followers 404 Following @AnthropicAI. Prev. @Google Brain/DeepMind, founding team @OpenAI. Computer scientist; inventor of the VAE, Adam optimizer, and other methods. ML PhD.
Shek Azizi @AziziShekoofeh
8K Followers 988 Following Staff Research Scientist @Google @GoogleDeepMind Opinions are my own.
Amber Yang @theamberyang
13K Followers 1K Following partner @lightspeedvp. cs + physics alum @stanford👩🏻💻
Alyssa @alyssakrejmas
8K Followers 6K Following Founder @withnouri blending thoughtful human care & tech to support parents • @theinnocrew supporting founders through events/authentic convos
David Hall @dlwh
3K Followers 1K Following Research Engineering Lead at @StanfordCRFM. Previously co-founder at Semantic Machines ⟶ MSFT. Lead developer of Levanter and Marin @[email protected]
The Kiffness @TheKiffness
162K Followers 371 Following Christian, husband, father, part time musician. EU & UK shows (Oct - Dec 2025) 🇪🇺 🇬🇧 https://t.co/FcKZbZmRo9
joyce @henloitsjoyce
16K Followers 3K Following personality hire @crossmint | prev many things | dms open