Nan Jiang @nanjiang_cs
machine learning researcher, with focus on reinforcement learning. assoc prof @ uiuc cs. Course on RL theory (w/ videos): https://t.co/vqVKwY4RJE nanjiang.cs.illinois.edu Joined November 2017-
Tweets2K
-
Followers10K
-
Following73
-
Likes13K
My 3rd blogpost on PG, the topic I am least familiar with but get asked a lot, so I thought I'd just put together the very limited stuff I know on this topic. Somehow the post gets cynical from time to time🙃 nanjiang.cs.illinois.edu/2025/09/29/pg.…
1
15
108
10K
72
Download Image
Nan Jiang retweeted
UTCS is hiring for several positions this year. Please share with anyone who may be interested! cs.utexas.edu/faculty/recrui…
Having used LLMs for helping with research (usually obscure issues/questions in technical lemmas), I'm getting the feeling that free ver of chatgpt is better than gemini 2.5 pro on this...?
For course notes that I update over years, what's the best practice? keep only the latest file, or keep all the major historical versions?
I was surprised by how many didnt know that (1) per token MLE is whole seq MLE, and (2) PG at token level same as PG at seq level (optimizkng one big combinatorial action). story is different if you introduce fitted critic/Q-values or intermediate resets.
I was surprised by how many didnt know that (1) per token MLE is whole seq MLE, and (2) PG at token level same as PG at seq level (optimizkng one big combinatorial action). story is different if you introduce fitted critic/Q-values or intermediate resets.
Nan Jiang retweeted
Microsoft Research New York City is seeking applicants for multiple Postdoctoral Researcher positions in ML/AI! These are positions for up to 2 years, starting in July 2026. Application deadline: October 22, 2025
shower thought: we model reward as fn of prompt & response but there are legit exceptions when questions are self-referential eg “r u strong in reasoning?” whose correct answer is policy dependent
useful & practical guidance for alignment! theorist nitpick: chi-square is more informative than KL on this matter. not that I expect huge diff in reality...
useful & practical guidance for alignment! theorist nitpick: chi-square is more informative than KL on this matter. not that I expect huge diff in reality...
from @PBSSpaceTime. once I told @JohnCLangford—who wrote a general relativity(!) paper around the time I interned at MSR—abt them and their first host being a Physics PhD working then at NSF. Turns out that was his coauthor on the GR paper… such a small world!
my 2nd blogpost: a rabbit hole I went down with a (wrong) trajectory-coupling interpretation of bisimulation metrics. gets quite technical but I'm glad I set up the blog, otherwise I wouldn't know where to share this :) nanjiang.cs.illinois.edu/2025/08/25/cou…
Nan Jiang retweeted
Once I supervised a project about pollen forecasting. That was eons ago with decision trees. After a year we did not beat the baseline that consists of using the previous day's value.
Once I supervised a project about pollen forecasting. That was eons ago with decision trees. After a year we did not beat the baseline that consists of using the previous day's value.
it is really an unfortunate convention that we choose to use d for occupancy in RL (e.g., d^pi)...
Nan Jiang retweeted
Announcing the first workshop on Foundations of Language Model Reasoning (FoRLM) at NeurIPS 2025! 📝Soliciting abstracts that advance foundational understanding of reasoning in language models, from theoretical analyses to rigorous empirical studies. 📆 Deadline: Sept 3, 2025
Nan Jiang retweeted
@DimitrisPapail @code_star chain rule for KL divergence: you have a token-level loss (good for optimization) but it gives you sequence-level control over behavior
Stats twitter: for IV regression E[Z X'] θ ≈ E[Z Y] (Z,X in R^d, θ in R^d, Y scalar), if I query a new x, LLM told me uncertainty is controlled by x' E[Z X']^{-1} E[ZZ'] (E[ZX']')^{-1} x, generalizing LR case (see concentration in pic). Is this legit? Ref to concentration bound?
Csaba Szepesvari @CsabaSzepesvari
11K Followers 722 Following "If there is not folly in the world, then the world itself is folly. You must understand that mistakes are not always regrets." - Paul Tobin, Bandette🤠
Eugene Vinitsky (@RLC... @EugeneVinitsky
21K Followers 2K Following This is the site where I talk about the attacks on science and immigration. Science is on the other site. Lab website: https://t.co/vrtbcqRyRn
Marc G. Bellemare @marcgbellemare
16K Followers 349 Following CSO & co-founder, Reliant AI. Ex RL research lead at Google Brain, DeepMind. Known for Atari 2600 RL benchmark, Distributional RL (MIT Press 2023).
Dan Roy @roydanroy
57K Followers 2K Following ML / AI researcher. Research Director and Canada CIFAR AI Chair, @VectorInst. Professor, @UofT (Statistics/CS).
Pablo Samuel Castro @pcastr
13K Followers 830 Following Señor swesearcher @ Google DeepMind. Adjunct prof @ U de Montreal & Mila. Musician. From 🇪🇨 living in 🇨🇦.
Kyunghyun Cho @kchonyc
78K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre physicist at @nyuniversity (@CILVRatNYU) & @PrescientDesign
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)
Behnam Neyshabur @bneyshabur
30K Followers 860 Following Research @AnthropicAI (Co-lead Discovery team) 💼 Past: Gemini @GoogleDeepMind (Co-led Blueshift team) 🧠 LLM Reasoning / AI Scientist 🎒Traveling & Backpacking
Michal Valko @misovalko
8K Followers 8K Following Building something new · Chief Models Officer @ Stealth Startup & Inria & MVA - Ex: Llama @AIatMeta Gemini and BYOL @GoogleDeepMind
Kevin Patrick Murphy @sirbayes
61K Followers 541 Following Research Scientist at Google DeepMind. Interested in Bayesian Machine Learning.
Ben Recht @beenwrekt
32K Followers 333 Following optimization. machine learning. uc berkeley. I blog at https://t.co/fkJujOPsJb The world won't end.
Natasha Jaques @natashajaques
31K Followers 1K Following Assistant Professor @uwcse and Staff Research Scientist at @GoogleAI. Let's get off this app: https://t.co/jbH2oAjbPN
Thomas G. Dietterich @tdietterich
58K Followers 625 Following Distinguished Professor (Emeritus), Oregon State Univ.; Former President, Assoc. for the Adv. of Artificial Intelligence; Robust AI & Comput. Sustainability
Yuandong Tian @tydsh
26K Followers 881 Following Research Scientist Director in Meta FAIR. Reasoning, Optimization and Understanding LLM. Novelist in spare time. PhD in @CMU_Robotics.
Sebastien Bubeck @SebastienBubeck
58K Followers 1K Following I work on AI at OpenAI. Former VP AI and Distinguished Scientist at Microsoft.
Amin Karbasi @aminkarbasi
11K Followers 3K Following Senior director of Cisco Foundation AI, Former Chief Scientist at Robust Intelligence. ex Professor at Yale University, ex staff research scientist at Google.
Prof. Anima Anandkuma... @AnimaAnandkumar
34K Followers 2K Following "Godmother" of AI+Science, Bren Professor @caltech, Time100, Fmr Sr Director of #AI research @nvidia Fmr Principal Scientist @awscloud
Gergely Neu @neu_rips
11K Followers 684 Following ML theory nerd & AI non-enthusiast. thinking a lot about online learning these days! BTW you should go find me on another website where i post more actively
Егор Купряш... @EKuprasin10144
0 Followers 60 Following
Seongsu Kim @sseongsukim
0 Followers 10 Following Reinforcement learning with data | M.S. Hanyang Univ.
Igajah @IgajahIg
172 Followers 3K Following
Harsha Bandi @harshadev12
143 Followers 4K Following AI Explorer | Web Developer | Software Engineer
aim mia @aimmia1646818
0 Followers 67 Following
Batsi Ziki @BatsiZiki
18 Followers 176 Following A budding Reinforcement Learning empiricist at @UCT_news
aoberai @aditya_oberai
814 Followers 691 Following
Balaji Varatharajan @BalajiAI
2K Followers 508 Following ML Nerd. Currently exploring diffusion models.
Sepehr Heidari @SepehrHeidari81
339 Followers 7K Following Interested in Physics🔭, Mathematics🧮, Computer Science 💻, and Dad Jokes🥸 https://t.co/jtKArilTEr
Ming Zhong @MingZhong_
2K Followers 923 Following PhD student at UIUC @dmguiuc | Research Intern at @GoogleDeepmind, @AIatMeta & @MSFTResearch
Jiazhi Yang @jiazhi_yang2024
339 Followers 2K Following PhD Student at MMLab, @CUHKofficial | Generative Models | Autonomous Driving | Robotics | World Models
Manish @algorithm_ml
2 Followers 120 Following Machine learning & Computer science function approximation
Xiang Zhou @XiangZhou14
487 Followers 694 Following Post-training Gemini @GoogleDeepMind, Ph.D. from @unccs
Tim Li @TimLi_DR
11 Followers 166 Following Co-Founder & CEO @DeepReach_ai | Building next-gen AI data & evaluation platform | Bridging global expert network with enterprise AI solutions
anuj @anujsesha
6 Followers 1K Following
Berlik Csanád @csanadberlik
0 Followers 15 Following
Ziyang Wu @robinwuzy
65 Followers 280 Following PhD student @berkeley_ai | Past: Intern @MSFTResearch
Irtiza🥺🤡🔪 @Ertezah
302 Followers 6K Following Restless | Fan of Tom in Tom&Jerry | Foodphilic | Symmetryphile | Favorite bird: Seagull |Lover of Art,Food and Books
Pietro @aplietexe
6 Followers 723 Following
John Lim @johnslim161
20 Followers 447 Following
Matthew Johnson @SingularMattrix
13K Followers 3K Following Researcher at Google Brain. I work on JAX (https://t.co/UGa5tGfinF).
Feishi Wang @FeishiWang
120 Followers 552 Following Graduate @PKU1898. Visiting @UCBerkeley. Learning RL
juknow @juknow_k
1 Followers 82 Following
guannan liu @guannanliu03
2 Followers 73 Following
Kazi Ershed Ahmed @ErshedAhmed1965
210 Followers 3K Following
Sarthak Garg @Sarthakhku
75 Followers 1K Following
Virul Dewnaka @startuplaybook
123 Followers 2K Following Exploring the depths of LLMs and shaping the future through hands-on experimentation
Guthrie Williamson @guthriejw
1K Followers 7K Following co-owner of: PORT LOCKROY, BOIS D’ARGENT, ZAAKI, GEAR UP, LAWS OF INDICES, BRUTAL. Same brand used by my father on: Great Klaire, Eight Carat, Cotehele House
dxnbewsn @dxnbewsn
9 Followers 2K Following
Buddy Hensler @BuddyHensl46582
2 Followers 314 Following
Chyma @ace_k8s
119 Followers 2K Following Cyber Security | K8s | ML enthusiast | Football (Arsenal) | MotorSports
Mikhail @mikhail_verw5
0 Followers 23 Following
Feng Yao @fengyao1909
1K Followers 662 Following Ph.D. student @UCSD_CSE | Intern @Amazon Rufus Foundation Model Ex. @MSFTResearch @TsinghuaNLP
Supreet Sahu @supreet_sahu
21 Followers 872 Following IIT Kharagpur @IITKgp '26 | 4th Year Undergrad @ ECE( Dual degree spl- Vision & Intelligent Systems) | AI/ML/DL/Computer Vision | Also on X : @SupreetSahu
Xun Wang @kunle1212
0 Followers 19 Following
yakoubY @YakoubYakoubov
122 Followers 1K Following
Shubhashis Roy Dipta @iamdipta007
256 Followers 1K Following MLR intern @AmazonScience || X-MLR @scale_AI || PhD @umbc || Multimodal (NLP + CV) || 🏠 https://t.co/XFDVDULOmq || 📝 https://t.co/UaVN46Jg3C
Clément Canonne (on ... @ccanonne_
37K Followers 65 Following Senior Lecturer @Sydney_Uni. Formerly Postdocs @IBMResearch, @Stanford; PhD @Columbia. Converts ☕ into puns: sometimes theorems. He/him. @ccanonne.bsky.social
Csaba Szepesvari @CsabaSzepesvari
11K Followers 722 Following "If there is not folly in the world, then the world itself is folly. You must understand that mistakes are not always regrets." - Paul Tobin, Bandette🤠
Sergey Levine @svlevine
110K Followers 133 Following Associate Professor at UC Berkeley Co-founder, Physical Intelligence
Marc G. Bellemare @marcgbellemare
16K Followers 349 Following CSO & co-founder, Reliant AI. Ex RL research lead at Google Brain, DeepMind. Known for Atari 2600 RL benchmark, Distributional RL (MIT Press 2023).
Kyunghyun Cho @kchonyc
78K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre physicist at @nyuniversity (@CILVRatNYU) & @PrescientDesign
Behnam Neyshabur @bneyshabur
30K Followers 860 Following Research @AnthropicAI (Co-lead Discovery team) 💼 Past: Gemini @GoogleDeepMind (Co-led Blueshift team) 🧠 LLM Reasoning / AI Scientist 🎒Traveling & Backpacking
Michal Valko @misovalko
8K Followers 8K Following Building something new · Chief Models Officer @ Stealth Startup & Inria & MVA - Ex: Llama @AIatMeta Gemini and BYOL @GoogleDeepMind
Ben Recht @beenwrekt
32K Followers 333 Following optimization. machine learning. uc berkeley. I blog at https://t.co/fkJujOPsJb The world won't end.
Thomas G. Dietterich @tdietterich
58K Followers 625 Following Distinguished Professor (Emeritus), Oregon State Univ.; Former President, Assoc. for the Adv. of Artificial Intelligence; Robust AI & Comput. Sustainability
Gergely Neu @neu_rips
11K Followers 684 Following ML theory nerd & AI non-enthusiast. thinking a lot about online learning these days! BTW you should go find me on another website where i post more actively
Yisong Yue @yisongyue
22K Followers 3K Following Machine Learning @Caltech (@YueLabCaltech). AI for invention at @AsariAILabs.
Jason Lee @jasondeanlee
18K Followers 4K Following Associate Professor at UC Berkeley. Former Research Scientist at Google DeepMind. ML/AI Researcher working on foundations of LLMs and deep learning.
Daniel Russo @DanielRuss0
1K Followers 143 Following Researcher. Prof of OR at Columbia. Tweeting about reinforcement learning.
Amir-massoud Farahman... @SoloGen
6K Followers 2K Following Goal: Understanding the computational and statistical principles required to design adaptive agents. Associate Prof @polymtl @Mila_Quebec 🇨🇦 #MahsaAmini
Sam Power @sp_monte_carlo
19K Followers 7K Following Lecturer in Maths & Stats at Bristol. Interested in probabilistic + numerical computation, statistical modelling + inference. @OnlineMCSeminar. (he / him)
Khimya @khimya
4K Followers 974 Following Research Scientist @GoogleDeepmind Affiliate Faculty @Mila_Quebec Past: PhD @mcgillu @MSFTResearch @Intel @UF @IITKanpur Bosch @VIT_univ she/her Views are mine!
Michael Littman @mlittmancs
8K Followers 152 Following
Sasha Rakhlin @rakhlin
33 Followers 15 Following
Audrey Huang @auddery
138 Followers 81 Following
Wen Sun @WenSun1
729 Followers 76 Following Assistant professor at @cornell_tech and research scientist at @Databricks; working on Reinforcement Learning.
Joelle Pineau @jpineau1
15K Followers 447 Following Chief AI Officer, @cohere Professor of Computer Science, @mcgillu Core academic member, @Mila_Quebec Ex-Meta (FAIR team)
Ching-An Cheng @ICML2... @chinganc_rl
2K Followers 101 Following Senior Research Scientist at @Google Research, working on usable theory and algorithms for Reinforcement Learning, Generative Optimization, and Robotics
shiemannor @shiemannor
296 Followers 12 Following Prof@Technion, Researcher@Nvidia, Founder@Jether Energy. Trying to get machine learning to really work.
Yu-Xiang Wang @yuxiangw_cs
4K Followers 349 Following Faculty @hdsiucsd, director of S2ML lab. Visitor @awscloud. Prev @ucsbcs @SCSatCMU. Researcher in #machinelearning, #reinforcementlearning, #differentialprivacy
Han Zhao @hanzhao_ml
3K Followers 1K Following Assistant Professor @siebelschool; Amazon scholar; Ph.D. @mldcmu; work on trustworthy machine learning and AI.
Alessandro Lazaric @alelazaric
126 Followers 4 Following
Thejakeyboy @Thejakeyboy
773 Followers 631 Following Associate Professor at Georgia Tech Computer Science. Machine Learning researcher. Former professional juggler 🤹🏻♀️, a career I aim to return to.
Nathan Kallus @nathankallus
2K Followers 238 Following 🏳️🌈👨👨👧👦 Assoc Prof @Cornell @Cornell_Tech @Netflix @NetflixResearch causal inference, experimentation, optimization, RL, statML, econML, fairness
mtelgars @mtelgars
694 Followers 55 Following
Debadeepta Dey @debadeepta
2K Followers 2K Following Principal Architect -AI Compiler, Microsoft | ex MSR, CMU
Yu Bai @yubai01
6K Followers 2K Following Research @OpenAI. Trained models for GPT5 Thinking / Mini; Contributor to gpt-oss, o3-mini, o1. Previously @SFResearch, PhD @Stanford.
Shimon Whiteson @shimon8282
18K Followers 422 Following Professor of Computer Science at Oxford. Senior Staff Research Scientist at Waymo.
Yuxi Li @yuxili99
909 Followers 196 Following Decentralized RL/AI. Guest editor, MLJ SI. Co-Chair for workshops in AAAI, ICML, NeurIPS. PhD @UAlberta.
Ofir Nachum @ofirnachum
5K Followers 356 Following Research at @OpenAI. Previously at @GoogleAI on the Brain Team. Doing work on #ReinforcementLearning and #MachineLearning
Zico Kolter @zicokolter
24K Followers 688 Following Professor and Head of Machine Learning Department at @CarnegieMellon. Board member @OpenAI and @Qualcomm. Chief Technical Advisor @GraySwanAI.
RL Theory Virtual Sem... @RLtheory
5K Followers 0 Following Virtual seminar series featuring the latest advances in theoretical reinforcement learning. Seminars (approximately) every Tuesday at 6pm UTC.
TalkRL Podcast @TalkRLPodcast
3K Followers 96 Following TalkRL Podcast is All Reinforcement Learning, All the Time. Follow for interviews with brilliant folks from across the world of RL. Host @robinc. DMs open.
Michael Kearns @mkearnsupenn
6K Followers 230 Following CS prof at Penn. Amazon Scholar. Interests in ML, fairness, privacy, algorithmic game theory, algo trading. Author of "The Ethical Algorithm" (with Aaron Roth).
Ruoyu Sun @RuoyuSun_UI
1K Followers 572 Following Associate Prof at CUHK-Shenzhen. Prev: assistant prof @UofIllinois; postdoc @Stanford; visitor @AIatMeta Work on optimization of machine learning, DL, LLM.
John Langford @JohnCLangford
10K Followers 43 Following Solving Machine Learning at Microsoft in New York. https://t.co/ZpdQV4IsHY pandemic past president. https://t.co/MkluiHpWF7 makes RL real. https://t.co/wK8xQaQGwf for thinking out loud.
Zhaoran Wang @zhaoran_wang
4K Followers 1K Following Associate Professor @NorthwesternU | PhD @Princeton | studying Reinforcement Learning
Bo Dai @daibond_alpha
3K Followers 795 Following Assistant Professor at @gtcse, Research Scientist at @GoogleDeepMind | ex @googlebrain
Yao Liu @yaoliucs
316 Followers 199 Following Research Scientist at AWS AI. Opinions are my own. Previously @AIforHI @StanfordAILab
Kianté Brantley (Hir... @xkianteb
2K Followers 1K Following Assistant Professor at Harvard | Fitness enthusiast | (He/Him/His)
Sham Kakade @ShamKakade6
16K Followers 497 Following Harvard Professor. Full stack ML and AI. Co-director of the Kempner Institute for the Study of Artificial and Natural Intelligence.
Rose Yu @yuqirose
9K Followers 582 Following Machine Learning Prof @UCSanDiego, Scholar @amazon, Previously @google, @Northeastern, @Caltech, @USC, #Physics-Guided #AI, MIT TR-35 Innovator.
Yuxin Chen @yuxinch
1K Followers 422 Following Machine Learning Researcher, Assistant Professor at @UChicagoCS
Jan Peters @Jan_R_Peters
5K Followers 416 Following #RobotLearning Professor (#MachineLearning #Robotics) at @ias_tudarmstadt of @TUDarmstadt (Part of @ELLISforEurope, @Hessian_AI and @DFKI)
Quanquan Gu @QuanquanGu
16K Followers 2K Following Professor @UCLA, Pretraining and Scaling at ByteDance Seed | Recent work: Build AGI | Opinions are my own
Lihong Li @LihongLi20
3K Followers 390 Following AI researcher in large language models, reinforcement learning & contextual bandits.
Andrej Risteski @risteski_a
3K Followers 2K Following Machine learning researcher. Associate Professor, ML department at CMU (@mldcmu).
Matt O'Dowd @matt_of_earth
12K Followers 66 Following Earthling, astrophysicist, professor at @LehmanCollege, Physics DEO at @GC_CUNY, associate at @AMNH, host & writer of @PBSSpaceTime, free to a good home
PBS SpaceTime @PBSSpaceTime
28K Followers 2K Following A PBS show about the universe! Written and hosted by astrophysicist Matt O'Dowd @matt_of_earthTrends for United States
6.349 posts
753 B posts
453 B posts
20,9 B posts
276 B posts
138 B posts
12,8 B posts
6.776 posts
11,9 B posts
7.354 posts
1.591 posts
135 B posts
2.122 posts
86,9 B posts
16,2 B posts
104 B posts
20,4 B posts
You might like
Tengyu Ma
@tengyuma
37K Followers
Shimon Whiteson
@shimon8282
18K Followers
Sham Kakade
@ShamKakade6
16K Followers
Sebastien Bubeck
@SebastienBubeck
58K Followers
Zico Kolter
@zicokolter
24K Followers
Marc G. Bellemare
@marcgbellemare
16K Followers
Ofir Nachum
@ofirnachum
5K Followers
Gergely Neu
@neu_rips
11K Followers
Elad Hazan
@HazanPrinceton
14K Followers
Brandon Amos
@brandondamos
20K Followers
Greg Yang
@TheGregYang
93K Followers
Sanjeev Arora
@prfsanjeevarora
25K Followers
Jakob Foerster
@j_foerst
21K Followers
Abhishek Gupta
@abhishekunique7
9K Followers
Deepak Pathak
@pathak2206
24K Followers