Chandan Singh @csinva
Seeking superhuman explanations. Senior researcher @MSFTResearch, PhD from @Berkeley_AI csinva.io Seattle, WA Joined February 2018-
Tweets373
-
Followers1K
-
Following570
-
Likes822
Title: Advice for a young investigator in the first and last days of the Anthropocene Abstract: Within just a few years, it is likely that we will create AI systems that outperform the best humans on all intellectual tasks. This will have implications for your research and…
Teaching a new course @Stanford this quarter on explainable AI, motivated by neuroscience. I have curated a paper list 4 pages long (link in comment). What are your favorite papers on explainable AI/mechanistic interpretability that I am missing? Please comment or DM. thanks!
“Bayesian concept bottleneck models using LLM priors” (BC-LLM) was accepted at #neurips2025! BC-LLM tackles a key clinical AI problem: how do we find interpretable features for predicting an outcome when there are ♾ possibilities from the electronic health record (e.g. notes)
🚀 ARE: scaling up agent environments and evaluations Everyone talks about RL envs so we built one we actually use. In the second half of AI, evals & envs are the bottleneck. Today we OSS it all: Meta Agent Research Environment + GAIA-2 (code, demo, evals). 🔗Links👇
😺Glad to share that our mixture-of-inputs paper is accepted at NeurIPS, see you in San Diego!
😺Glad to share that our mixture-of-inputs paper is accepted at NeurIPS, see you in San Diego!
🚨 New paper alert 🚨 Using LLMs as data annotators, you can produce any scientific result you want. We call this **LLM Hacking**. Paper: arxiv.org/pdf/2509.08825
Google presents an AI system to write expert-level scientific software. Using LLMs + tree search, it invented novel methods in bioinformatics, epidemiology, geospatial analysis & more, often surpassing human SOTA. (1/4)
New Open dataset alert: 🧠 Introducing "Spacetop" – a massive multimodal fMRI dataset that bridges naturalistic and experimental neuroscience! N = 101 x 6 hours each = 606 functional iso-hours combining movies, pain, faces, theory-of-mind and other cognitive tasks! 🧵below
Instructions/reasoning are now everywhere in retrieval - we want embeddings to do it all! 🚀 But... is it even possible? 🤔 Turns out, it's not possible for single-vector models 😱 theoretically and empirically! To make it obvious we OSS a simple eval SoTA models flop on! 🧵
Glad to share that our paper was accepted the main EMNLP 2025 Conference! x.com/Sahil1V/status…
Glad to share that our paper was accepted the main EMNLP 2025 Conference! x.com/Sahil1V/status…
This is (imo) the single most important result in any modern language encoding study. 35 interpretable yes/no questions gets the same neural predictivity as an LLM. No deep mechanistic similarity to the brain required; any model that can represent these features would do.
This is (imo) the single most important result in any modern language encoding study. 35 interpretable yes/no questions gets the same neural predictivity as an LLM. No deep mechanistic similarity to the brain required; any model that can represent these features would do.
New paper with @NeuroRJ, @csinva, @SunaGuo, Gavin Mischler, Jianfeng Gao, & @NimaMesgarani: We use LLMs to generate VERY interpretable embeddings where each dimension corresponds to a scientific theory, & then use these embeddings to predict fMRI and ECoG. It WORKS!
New paper with @NeuroRJ, @csinva, @SunaGuo, Gavin Mischler, Jianfeng Gao, & @NimaMesgarani: We use LLMs to generate VERY interpretable embeddings where each dimension corresponds to a scientific theory, & then use these embeddings to predict fMRI and ECoG. It WORKS!
In our new paper, we explore how we can build encoding models that are both powerful and understandable. Our model uses an LLM to answer 35 questions about a sentence's content. The answers linearly contribute to our prediction of how the brain will respond to that sentence. 1/6
Evaluating scientific theories as predictive models in language neuroscience biorxiv.org/content/10.110… #biorxiv_neursci
Are you compositionally curious 🤓 Want to know how to learn embeddings using🌲? In our new #ICML2025 paper, we present Banyan: A recursive net that you can train super efficiently for any language or domain, and get embeddings competitive with much much larger LLMs 1/🧵
Sebastian Raschka @rasbt
359K Followers 1K Following ML/AI researcher & former stats professor turned LLM research engineer. Author of "Build a Large Language Model From Scratch" (https://t.co/O8LAAMRzzW).
Rosanne Liu @savvyRL
46K Followers 1K Following (On mat leave.) Cofounded & running @ml_collective. Host of Deep Learning Classics & Trends. Research at Google DeepMind. DEI/DIA Chair of ICLR & NeurIPS.
𝙷𝚒𝚖𝚊 𝙻... @hima_lakkaraju
16K Followers 1K Following AI Professor @Harvard; Senior Staff Research Scientist @GoogleAI; @trustworthy_ml #AI #Safety #XAI; AI PhD from Stanford; Sloan/Kavli Fellow, MIT TR #35Under35
Horace He @cHHillee
42K Followers 538 Following @thinkymachines Formerly @PyTorch "My learning style is Horace twitter threads" - @typedfemale
Sunnie S. Y. Kim ☀�... @sunniesuhyoung
2K Followers 2K Following Research Scientist @Apple 👩💻 Responsible AI & Human-AI Interaction ✨️ Prev @PrincetonCS PhD, @Yale BSc, @MSFTResearch @TTIC_Connect Intern
Peter Hase @peterbhase
3K Followers 1K Following Visiting Scientist at Schmidt Sciences. Visiting Researcher at the Stanford NLP Group Previously: Anthropic, AI2, Google, Meta, UNC Chapel Hill
Chhavi Yadav @chhaviyadav_
3K Followers 3K Following @mldcmu | Trustworthy and Reliable AI | ZKPs | PhD from @ucsd_cse | @trustworthy_ml
Brihi Joshi @BrihiJ
2K Followers 4K Following PhD-ing @nlp_usc🏝 + @AmazonScience @Apple Fellow, ex-@IIITDelhi. Sky pics, #NLProc, @5sos and cat content, mostly thinking about “useful” AI
Glennie @g_emery28
287 Followers 3K Following
CosmicVoyager @dawenx_D
9 Followers 97 Following
Linnea Evanson, PhD @EvansonLinnea
377 Followers 331 Following Postdoc | Former PhD Student @ École Normale Supérieure | Former Research Scientist Intern @ Meta AI | Studying how AI and our brains learn language!
Robert Scoble @Scobleizer
543K Followers 24K Following The best from ML/AI community | Ex-Microsoft, Rackspace, Fast Company | Wrote eight books about the future | Silicon Valley robots, holodecks, BCIs, & startups.
Parshin Shojaee @ParshinShojaee
3K Followers 1K Following PhD student @VT_CS | AI for Science, Math, Code, Reasoning | Intern @Apple | prev @Adobe
Dr. Candice Chi-Hang ... @CandiceCheung12
1K Followers 2K Following Guest researcher with the focus on #Autism Spectrum Disorder and #linguistics @AutismINSAR | @AutismScienceFd | @AutismEurope | @LingSocAm | @APA
Nurdaulet Mukhituly @mukhitson
72 Followers 269 Following PhD @MBZUAI, doing AI Safety and Interpretability
Jung, Heejung @jungheejung_
37 Followers 93 Following Postdoc @Stanford mapping the neural representations of the "future" | How do expectations about people, pain, and possibilities shape perception in real-time?
degen_bobo 🤖💎 @agostino90
747 Followers 5K Following
Suna @_Sunanana
28 Followers 137 Following
Julius Adebayo @juliusadml
2K Followers 1K Following Building @guidelabsai - Engineering interpretable models and agents that are easy to audit.
Cornell Bogisich @CBogisich42840
126 Followers 3K Following
Sam Nastase @samnastase
2K Followers 2K Following assistant professor of psychology @USC丨he/him丨semiprofessional dungeon master丨🍉
Patrick Drake @time8machine
17K Followers 6K Following Neurodivergent physics student with a keen interest in multisensory integration and emergent perception. Exploring research on a proposed ‘sixth sense’. Δ
Uttara Khatri @UttaraKhatri28
260 Followers 569 Following Neuroscience trainee | PhD candidate @UTAustin @UTexasKHE @utexasrms | BS-MS @IiserTirupati | Neuro, TMS, stroke rehab, ML, NLD, art, outdoor-sy.
j @JC_9_1_1
34 Followers 623 Following
![[In thick Austrian accent] Just some guy, you know.](https://pbs.twimg.com/profile_images/378800000709778870/cca78522d1f78af68d02505415d8fd2e.jpeg)
Morgan Hough (mhough.... @mhough
764 Followers 5K Following [In thick Austrian accent] Just some guy, you know.
Rahul Chauhan @ChauhanRah69779
6 Followers 218 Following “AI/ML Engineer | Built RAG-EngineX: Modular RAG Framework | LangChain & LangSmith enthusiast | Open to collaborations & learning”
Emin Çelik @emincelik
191 Followers 503 Following Postdoc @mpi_sws_ working at the intersection of neuroscience, machine learning, and NLP. Prev. @BilkentUniv, @UTAustin.
Badr AlKhamissi @bkhmsi
1K Followers 1K Following PhD @EPFL_en Ex @MetaAI, @SonyAI_global, @Microsoft MSc @CoCoNeuro_Gold BSc CS @AUC Egyptian 🇪🇬
Xinting Huang @huangxt233
129 Followers 124 Following PhD student https://t.co/9nBzEDGpxu currently working on interpretability of neural models https://t.co/5aNeNJBqnF
vikram @tensortantrum
0 Followers 122 Following “Maybe the KV cache was the friends we made along the way.”
Anna Ivanova @neuranna
5K Followers 1K Following Language and thought in brains vs machines. New Assistant Prof @ Georgia Tech Psychology. Previously: postdoc @MIT_Quest & PhD @mitbrainandcog. She/her
Kashish Jagga @kashish_jagga
23 Followers 3K Following
Valentina Tardelli @ValentinaT32922
84 Followers 6K Following
Pranav Pawar @KagglePawar
6 Followers 159 Following AI Researcher | Evolution is a mystery, Clock makes a fool of history |
Trimfinity @trimfinity001
32 Followers 703 Following At Trimfinity, as a Zoho-authorized partner - we specialize in helping enterprises and small businesses streamline and automate their existing business process.
Mattia Opper @zvez11
79 Followers 269 Following Phd @an_exlab @EdinburghNLP @InfAtED trying to make ML models more efficient and explainable through inductive biases. Supervised by Siddharth N. and Ivan Titov
Jaeyoung Lee @lee__jaeyoung
123 Followers 718 Following Doing research on MLLM/LLM | Automated/Mechanistic Interpretability | prev: @SeoulNatlUni
two-faced bitch @shmk_m
86 Followers 665 Following husband. wife. uncle. daughter. proud alumnus. working on something nude.
Koyena Pal @kpal_koyena
270 Followers 243 Following Ph.D. Student @KhouryCollege | Interpretable AI + Data Science | BS/MS @BrownCSDept
seedawk @wiredguys
93 Followers 228 Following quote unquote engineer / expert at eloc screed https://t.co/v9wjNPXJQh
Oğuzhan @byyildirim07
276 Followers 773 Following per aspera ad astra | comp eng’ https://t.co/odoZz5yLW9
Arindam @halg0rithmist
30 Followers 1K Following 22 Aspiring theoretician Interested in decision making algorithms
Taratorn Asssawadejme... @assawa__
8 Followers 70 Following
Allan Zapata @azapsoul
5 Followers 127 Following I build weird and useful AI tools, post experiments daily - Data Science student @UNIVERSIDAD_PMA.
Saurav Patel @sauravkpatel
4 Followers 250 Following
Chance @ChanceMathisen
142 Followers 2K Following
Sebastian Raschka @rasbt
359K Followers 1K Following ML/AI researcher & former stats professor turned LLM research engineer. Author of "Build a Large Language Model From Scratch" (https://t.co/O8LAAMRzzW).
Rosanne Liu @savvyRL
46K Followers 1K Following (On mat leave.) Cofounded & running @ml_collective. Host of Deep Learning Classics & Trends. Research at Google DeepMind. DEI/DIA Chair of ICLR & NeurIPS.
Sameer Singh @sameer_
7K Followers 2K Following Cofounder/CTO @SpiffyAI and Prof at @UCIrvine, working on reliable LLMs, explanations for AI+ML, adversaries for NLP, and debugging/evaluation.
𝙷𝚒𝚖𝚊 𝙻... @hima_lakkaraju
16K Followers 1K Following AI Professor @Harvard; Senior Staff Research Scientist @GoogleAI; @trustworthy_ml #AI #Safety #XAI; AI PhD from Stanford; Sloan/Kavli Fellow, MIT TR #35Under35
Horace He @cHHillee
42K Followers 538 Following @thinkymachines Formerly @PyTorch "My learning style is Horace twitter threads" - @typedfemale
Sunnie S. Y. Kim ☀�... @sunniesuhyoung
2K Followers 2K Following Research Scientist @Apple 👩💻 Responsible AI & Human-AI Interaction ✨️ Prev @PrincetonCS PhD, @Yale BSc, @MSFTResearch @TTIC_Connect Intern
Jascha Sohl-Dickstein @jaschasd
26K Followers 718 Following Member of the technical staff @ Anthropic. Most (in)famous for inventing diffusion models. AI + physics + neuroscience + dynamics.
Peter Hase @peterbhase
3K Followers 1K Following Visiting Scientist at Schmidt Sciences. Visiting Researcher at the Stanford NLP Group Previously: Anthropic, AI2, Google, Meta, UNC Chapel Hill
Chhavi Yadav @chhaviyadav_
3K Followers 3K Following @mldcmu | Trustworthy and Reliable AI | ZKPs | PhD from @ucsd_cse | @trustworthy_ml
Ben Brubaker @benbenbrubaker
2K Followers 1K Following Staff writer @QuantaMagazine covering computer science. Former freelance physics writer, ex-physicist. Same handle at bluesky and mastodon.
Patrick Vossler @ppatrickv
77 Followers 150 Following @UCSF data scientist working on monitoring machine learning methods, LLM-as-a-Judge, and more!
Simran Arora @simran_s_arora
5K Followers 207 Following building ai systems, cs phd @stanford @hazyresearch, incoming asst. prof. @caltech
Parshin Shojaee @ParshinShojaee
3K Followers 1K Following PhD student @VT_CS | AI for Science, Math, Code, Reasoning | Intern @Apple | prev @Adobe
Joachim Baumann @joabaum
192 Followers 822 Following Postdoc @MilaNLProc / Incoming Postdoc @StanfordNLP @StanfordAILab / Prev: @UZH_en @MPI_IS @CarnegieMellon. CompSocSci, LLMs, algorithmic fairness.
Tim van Erven @tverven
1K Followers 176 Following Associate professor in machine learning at the University of Amsterdam. Topics: (online) learning theory and the mathematics of interpretable AI.
Nurdaulet Mukhituly @mukhitson
72 Followers 269 Following PhD @MBZUAI, doing AI Safety and Interpretability
Jung, Heejung @jungheejung_
37 Followers 93 Following Postdoc @Stanford mapping the neural representations of the "future" | How do expectations about people, pain, and possibilities shape perception in real-time?
Naomi Saphra @nsaphra
10K 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.
Orion Weller @orionweller
2K Followers 951 Following PhD student @jhuclsp interning @AIatMeta FAIR. Prev intern @GoogleDeepMind, @samaya_ai, @allen_ai. Research: LLMs, RAG, and IR
Niklas Muennighoff @Muennighoff
9K Followers 475 Following Researching AI/LLMs @Stanford @ContextualAI @allen_ai
Julius Adebayo @juliusadml
2K Followers 1K Following Building @guidelabsai - Engineering interpretable models and agents that are easy to audit.
Maria Ryskina (✈️... @maria_ryskina
1K Followers 597 Following Postdoc @VectorInst | Ex @mcgovernmit, @LTIatCMU | she/they | 🤍💙🤍
Jean Zarate / Lady Gi... @lady_ginseng
883 Followers 634 Following Chief Scientist for Comms/Engagement at CPNE. Former editor @NatureNeuro. All actions are my own. Singer-songwriter. Actor. Daydreams of sleeping.
Micha Heilbron @m_heilb
2K Followers 1K Following Assistant Professor of Cognitive AI @UvA_Amsterdam, @AmsterdamBrain. cognitive science 🤝 AI 🤝cognitive neuroscience. 🟦 mheilbron.bsky
Sam Nastase @samnastase
2K Followers 2K Following assistant professor of psychology @USC丨he/him丨semiprofessional dungeon master丨🍉
Patrick Drake @time8machine
17K Followers 6K Following Neurodivergent physics student with a keen interest in multisensory integration and emergent perception. Exploring research on a proposed ‘sixth sense’. Δ
Roberta Raileanu @robertarail
9K Followers 2K Following Senior Staff Research Scientist @GoogleDeepMind & Honorary Lecturer @UCL. ex @Meta|@MSFTResearch|@NYU|@Princeton. Llama-3, Toolformer, Rainbow Teaming, MLGym.
Noémi Éltető @EltetoNoemi
2K Followers 617 Following AI-like human interested in human-like AI; working on thesis (stealth mode); research scientist at DeepMind 🇬🇧; previously 🇩🇪, 🇭🇺, 🇷🇴
Emin Çelik @emincelik
191 Followers 503 Following Postdoc @mpi_sws_ working at the intersection of neuroscience, machine learning, and NLP. Prev. @BilkentUniv, @UTAustin.
Suna @_Sunanana
28 Followers 137 Following
Badr AlKhamissi @bkhmsi
1K Followers 1K Following PhD @EPFL_en Ex @MetaAI, @SonyAI_global, @Microsoft MSc @CoCoNeuro_Gold BSc CS @AUC Egyptian 🇪🇬
Albert Ge @albert_ge_95
129 Followers 197 Following now PhD influencer @WisconsinCS, then @Harvard_IACS @caltech
Sarah Wiegreffe @sarahwiegreffe
5K Followers 1K Following Research in NLP (mostly LM interpretability & explainability). Assistant prof @umdcs @clipumd Formerly @allen_ai @uwnlp @icatgt @gtcomputing Views my own.
Xinting Huang @huangxt233
129 Followers 124 Following PhD student https://t.co/9nBzEDGpxu currently working on interpretability of neural models https://t.co/5aNeNJBqnF
Andrew Lampinen @AndrewLampinen
9K Followers 2K Following Interested in cognition and artificial intelligence. Research Scientist @DeepMind. Previously cognitive science @StanfordPsych. Tweets are mine.
Anna Ivanova @neuranna
5K Followers 1K Following Language and thought in brains vs machines. New Assistant Prof @ Georgia Tech Psychology. Previously: postdoc @MIT_Quest & PhD @mitbrainandcog. She/her
Nima Mesgarani @NimaMesgarani
737 Followers 112 Following Associate professor at Columbia University. Interested in speech neuroscience and speech technologies.
Mattia Opper @zvez11
79 Followers 269 Following Phd @an_exlab @EdinburghNLP @InfAtED trying to make ML models more efficient and explainable through inductive biases. Supervised by Siddharth N. and Ivan Titov
Freda Shi @fredahshi
3K Followers 849 Following Assistant Professor @UWCheritonCS, @CIFAR_News AI Chair @VectorInst, @ReviewAcl Co-CTO | PhD @TTIC_Connect | BS @PKU1898 | Excited about "grounding" in any form
Ari Holtzman @universeinanegg
3K Followers 2K Following Asst Prof @UChicagoCS & @DSI_UChicago, leading Conceptualization Lab https://t.co/BVCT3zdaNV Minting new vocabulary to conceptualize generative models.
Koyena Pal @kpal_koyena
270 Followers 243 Following Ph.D. Student @KhouryCollege | Interpretable AI + Data Science | BS/MS @BrownCSDept
Hasson Lab @HassonLab
4K Followers 205 Following The latest news from Uri Hasson's cognitive neuroscience research group at Princeton University
Jiacheng Lin @jclin808
145 Followers 277 Following CS PhD candidate @ UIUC; DeepRetrieval, Rec-R1; LLM&RL&Healthcare; Undergrad&MS @Tsinghua_Uni; Intern@UW, Amazon, Microsoft, Keiji AI
Dibya Ghosh @its_dibya
3K Followers 455 Following @AnthropicAI | Made friends along the way @UCBerkeley @ Google Brain Montreal, @physical_int
Harry Thasarathan @HThasarathan
276 Followers 408 Following PhD student @YorkUniversity @LassondeSchool, I work on computer vision and interpretability.
Shangshang Wang @UpupWang
441 Followers 146 Following Phd student in CS + AI @CSatUSC. CS undergrad, master @ShanghaiTechUni. LLM reasoning, RL, mechanistic interpretability, AI4Science.
BrainGate Team @BrainGateTeam
2K Followers 17 Following A consortium of clinicians, scientists, and engineers developing brain-computer interfaces to restore movement and communication for people with paralysis
Lily Weng @LilyWeng_
22 Followers 11 Following Assistant Professor at @UCSanDiego, lead the Trustworthy ML Lab. PhD from @MIT.
Arnav Das @arnaved
90 Followers 350 Following
Mariya Toneva @mtoneva1
3K Followers 581 Following Faculty at @mpi_sws_ working at the intersection of ML, NLP, and cognitive neuroscience. Yogurt snob.Trends for United States
You might like
