Anurag Koul (अनुराग कौल) @koulanurag
PostDoctoral Researcher @ Microsoft Research | Deep Reinforcement Learning koulanurag.dev New York, NY, USA Joined May 2010-
Tweets247
-
Followers154
-
Following587
-
Likes817
One thing in AI research that I have finally recognized with clarity is the idea of “inertia bias”: continuing to do something when it’s not the best option. The most basic instance of inertia bias is the feeling of “I already spent time implementing X, so let me continue trying…
India 🇮🇳- People in Varanasi, Uttar Pradesh offer prayers in Ganga river as they extend support to Israel. @rekatz @ABSamson1 @HusseinAboubak @patrickbetdavid @monicaonairtalk @realDrewMullins @andrewbostom @chrismartenson @ABSamson1 @RealCynicalFox @Schizointel @BeharGiacomo…
This is a huge moment. Using a learned policy, Cassie set a world record. 🥇🎉
This is a huge moment. Using a learned policy, Cassie set a world record. 🥇🎉
Video lectures, UC Berkeley EE 290-2 Hardware for Machine Learning spring 2021, by Sophia Shao inst.eecs.berkeley.edu/~ee290-2/sp21/
When teaching academic writing at the PhD level, here are 5 tools I recommend. A 🧵⬇️:
Take 34 seconds to watch Saturn appear from behind the Moon. And marvel at the fact that we live in a remarkable and beautiful planetary system. Video source: bit.ly/3fCWTci
जब airport पर आपको 12-15 लोग बोलें,”आपकी #TheKashmirFiles देखी! Sorry! हमें पता ही नहीं था कि #KashmiriPandits के साथ ये सब हुआ था।” और फिर security officer कहे,” खेर साहब! आपकी फ़िल्म ने दहला दिया!” तो इसका मतलब है हमारी फ़िल्म लोगों के दिलों तक जा रही है।झकझोर रही है! जय हो!🙏
India is at war. But nobody is telling you. Not anymore. Pl watch the trailer of the most Brutally Honest story of Kashmir Genocide. Pl share ONLY if you like it. #TheKashmirFiles #RightToJustice youtu.be/A179apttY58
Beauty lies within but if you’ll go deep in the history of Kashmir you’ll find a #LostParadise. #TheKashmirFiles releasing on 11th March ONLY IN THEATRES #RightToJustice
ANNOUNCEMENT: #TheKashmirFiles is releasing in THEATRES on March 11. Bringing the story of #KashmiriPanditGenocide Please support and bless us. 🙏 #KashmiriPanditGenocide
Today completes 32 years of #KashmiriPanditGenocide!Thousands of innocent people were killed & women raped. World has turned a blind eye to this biggest human tragedy. My nalmot (hug in Kashmiri) to all the families of the victims of this horrible genocide!💔 #KashmirGenocide1990
Delighted to announce that our paper (arxiv.org/abs/2006.03745) w/ @koulanurag, Alan Fern, @GreenWithE on RL agents' interpretability has been accepted to #ICML 2021. In the paper, we ask the question on how much we really understand Recurrent Network RL policies?
✍️Want to learn more about RL, generalization within & across tasks as well as the ‚reward is enough hypothesis‘ 🌍🔄🤖? Checkout a set of thought-provoking talks by @matteohessel, @aharutyu and David Silver at the @M2lSchool ✌️
Real Multi Agent RL! @hardmaru #RL #AI #MachineLearning #DeepLearning #Tech
Here I describe a brief overview of how the Pfizer/BioNTech or Moderna mRNA vaccines work. Taking a vaccine is one’s personal choice, and I hope this video can help someone make that decision rooted in science.
Anyone overwhelmed by the sheer number of NeurIPS talks one could listen to? Please post ones your excited about, not including your own or close colleagues.
Here’s a free Machine Learning lecture series covering half of Bishop's PRML book! 🥳 Just made a page and Youtube channel w videos+pdfs I used in teaching "ML 1" to our fresh #Master #AI @UvA_Amsterdam students. 🧐uvaml1.github.io🧐 📺youtube.com/playlist?list=…📺
Here's a 40-minute summary of 15 years of research in Markov logic: youtube.com/watch?v=VgELbD…
How to WOW R2 with your #AI Don't say: “I am using A* search” When you can say: “I am doing DeepRL on DecPOMDPs, with non-multiple agents, non-stochastic actions in non-continuous non-hidden state space, non-negative transition costs and available transition and reward models”
Princess Blankschan @BlankschPrinc
0 Followers 45 FollowingNicky Milkowski @MilkowsNic
79 Followers 5K FollowingSuessew @SuessewOlsrG
0 Followers 185 FollowingTetenanoa @tetenanoa83818
22 Followers 305 Following Nice to meet you. My hobbies are reading, food and sports. I like cats😘 I like to meet new friends while traveling🎉🎉🎉Anupriya Hartsell @AnupriH
77 Followers 5K FollowingNu Freeburger @Freeburger470
131 Followers 5K FollowingDaisy-may Mangine @MangineMay79974
79 Followers 5K FollowingMilana Halechko @m_halech
47 Followers 5K FollowingDorisMarshall @S7KH8I58O1UCO
0 Followers 223 FollowingDeandra Magliocca @DeandraMag94815
84 Followers 5K FollowingElizabeth Balbin @balbin_balb
61 Followers 5K FollowingArie Pleitez @arie_plei
51 Followers 5K FollowingCaroline Young @CarolineYo15211
38 Followers 790 FollowingAaria Worsfold @WorsfAa
77 Followers 5K FollowingEugene Vinitsky @EugeneVinitsky
13K Followers 2K Following Lets make multi-agent learning easy. Anti-cynic. RS at Apple, Asst. Prof at @nyutandon. He/him. Anonymous feedback: https://t.co/Mmmg7uPm1tEllie-may Pozzobon @MayPozzobo69303
36 Followers 5K FollowingMadalyn Gunselman @MadaGunselm
76 Followers 5K FollowingRenda Landfried @LandfriedR18877
89 Followers 5K FollowingAyla Durrah @AylaD56383
90 Followers 5K FollowingJennell Mccaffity @jenn_mccaff
36 Followers 5K FollowingSummer-rose Achter @AchterRose2567
73 Followers 5K FollowingKathey Debow @KatDebow
46 Followers 5K FollowingDenyse Wholey @DenyWhol
86 Followers 5K FollowingSue Rebuldela @RebuldelaS17412
30 Followers 5K FollowingFelisha Busic @bus_felis
47 Followers 5K FollowingNa Ortelt @NOrtelt32733
15 Followers 3K FollowingSydney Wand @SydneyWand2300
28 Followers 5K FollowingNasytha @Nasytha111443
40 Followers 2K FollowingLilly @lilly_lilly1856
1 Followers 53 Following "There are no secrets to success. It is the result of preparation, hard work, and learning from failure."Brittni Larribeau @britt_larrib
44 Followers 5K FollowingLilli Harshfield @LilHarshfiel
37 Followers 5K FollowingTatum Sobotta @TatuSobott
52 Followers 5K FollowingFetiseath @fetiseath11748
38 Followers 1K Following I live alone now and enjoy business, traveling, shopping, food and music. I have a calm personality and I hope we can be friends.McSteree @steree94820
77 Followers 1K Following I live alone now and enjoy business, traveling, shopping, food and music. I have a calm personality and I hope we can be friends.Amineh Zadbood @amiinehz
186 Followers 1K Following Adjunct Faculty and Research Associate at @followstevens; machine learning, large language models; optimization; agent-based modelingElliot @meldrum2718
35 Followers 268 Followingautistic @autistic614022
0 Followers 99 Following Studied crypto I'm in https://t.co/snpOcNKhcp last year, earned over $2M, achieved financial freedom, This has enabled me to kick-start my global travel plan!Ethan Xu @LinjieXu
161 Followers 601 Following 3rd-year PhD stu. at @GameAI_QMUL. Now interning at Microsoft Research Beijing. Working on Reinforcement Learning.Sumedh Pendurkar @SumedhPendurkar
45 Followers 255 Following PhD student Comp Sci. Dept Texas A&M university.Haoyu Xiong @Haoyu_Xiong_
2K Followers 2K Following Student researcher @CMU_Robotics/ I work on robotic agents in the real world #robotlearningClaudio Aldana @claudio_aldana
94 Followers 529 Following $NVDA investor AI accelerationist, Bitcoin maximalist, lean libertarian.Chloé Rouyer @RouyerChloe
131 Followers 190 Following Postdoc at Montanuniversität, Leoben. Previously @DIKU_institut. I like Bandits.Akanksha Saran @AkankshaSaran
579 Followers 956 Following Research Scientist in the Reinforcement Learning Group at Sony Research.Wadhwani School of Da.. @WSAI_IITM
157 Followers 17 Following Official handle of the Wadhwani School of Data Science & AI (WSAI) @iitmadras. Home to several research centres and the Dept. of DSAI (@DSAI_IITM)VITA Group @VITAGroupUT
781 Followers 2K Following VITA Group @ UT Austin w/ Prof Atlas Wang | https://t.co/OCxY1858GB Run by VITA students (PI says he doesn't care 😄). Tweets only reflect personal viewsProf. Anima Anandkuma.. @AnimaAnandkumar
25K Followers 2K Following Bren Professor @caltech, Fmr Sr Director of #AI research @nvidia, Fmr Principal Scientist @awscloud, AI+Science, PDE, Neural operators. Views my own.Eugene Vinitsky @EugeneVinitsky
13K Followers 2K Following Lets make multi-agent learning easy. Anti-cynic. RS at Apple, Asst. Prof at @nyutandon. He/him. Anonymous feedback: https://t.co/Mmmg7uPm1tVikas Sindhwani @vikassindhwani
760 Followers 202 Following Artificial Intelligence and Robotics Researcher @Google (Tweets are my own and unrelated in any way to my employer).Physical Intelligence @physical_int
4K Followers 8 Following Physical Intelligence (Pi), bringing AI into the physical world.Jim Fan @DrJimFan
230K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Josiah Hanna @JosiahHanna
315 Followers 134 Following Reinforcement Learning and Robotics Assistant Prof at University of Wisconsin -- MadisonDaniel Brown @daniel_s_brown
727 Followers 112 Following Assistant professor at University of Utah. Researching robot learning, reward/imitation learning, HRI, and AI safety.RL_Conference @RL_Conference
2K Followers 240 Following Home of the first annual reinforcement learning conference. Stay tuned up for updates!Stephen Wolfram @stephen_wolfram
149K Followers 4 Following Creating ideas, technology, science, companies, books, ... #WolfLang #WolframPhysics #WolframAlpha #Mathematica @WolframResearchwill grathwohl @wgrathwohl
4K Followers 237 Following Lover of raccoons and machine learning. Research Scientist at @GoogleDeepMind in NYC. Ph.D. from @UofTCompSciShek Azizi @AziziShekoofeh
7K Followers 997 Following Staff Research Scientist @Google @GoogleDeepMind 🧠 Opinions are my own.Konstantin Mishchenko @konstmish
4K Followers 563 Following Research Scientist at Samsung AI Center Outstanding Paper Award @icmlconf 2023 Action Editor @TmlrOrg I tweet about ML papers and mathLenka Zdeborova @zdeborova
13K Followers 422 Following Professor at EPFL. Une mathémaphysinformaticienne. Passionate mushroom hunter. Tamer of two little dragons.Nitish Srivastava @nitishsr
4K Followers 140 Following Co-Founder and CTO at Vayu Robotics; Machine Learning for Robotics and Autonomous SystemsAlexis Conneau @alex_conneau
24K Followers 113 Following Audio AGI Research Lead @OpenAI - "Hear the AGI"Neuralink @neuralink
1.4M Followers 1 Following Creating a general-purpose, high-bandwidth interface to the brainIndia in USA @IndianEmbassyUS
198K Followers 1K Following Official Twitter account of the Embassy of India, Washington, DC. #Passport Issue @IndiaPassportDC #Visa @IndiaVisaDC #OCI @IndiaOCIDCIndia in New York @IndiainNewYork
34K Followers 785 Following Welcome to the Official Twitter Account of the Consulate General of India, New York. For any queries use Pramit helpline available on our website.Chen Sun 🧠🤖🇨.. @ChenSun92
983 Followers 335 Following Mathematician at heart. Sometimes thinks about brains. Banting Fellow @ Mila || ex MIT, Cambridge, IMOAccepted papers at TM.. @TmlrPub
3K Followers 2 FollowingTransactions on Machi.. @TmlrOrg
5K Followers 3 Following Transactions on Machine Learning Research (TMLR) is a new venue for dissemination of machine learning researchMarc Brockschmidt @mmjb86
1K Followers 131 Following Learning to learn about structured things (molecules, programs, ...) @GoogleAI. Ex @MSFTResearchCam, ex @Debian. Opinions my own.Behnam Neyshabur @bneyshabur
18K Followers 690 Following Senior Staff Research Scientist @GoogleDeepMind, Interested in reasoning w. LLMs, traveling & backpackingElise van der Pol @ElisevanderPol
3K Followers 508 Following Senior Researcher at Microsoft Research Amsterdam. Structure, symmetry and equivariance in RL and AI4Science. She/her.Murray Shanahan @mpshanahan
16K Followers 313 Following Professor at Imperial College London and Principal Scientist at Google DeepMind. Tweeting in a personal capacity. To send me a message please use emailJordan Ash @jordan_t_ash
854 Followers 113 Following Senior researcher @MSFTResearch NYC. PhD from Princeton's CS department.Daniele Magazzeni @DanMagazzeni
711 Followers 348 Following Managing Director & Head of Explainable AI Center of Excellence at JPMorgan (Hiring!). Visiting Professor at King's College London. Opinions mine.Decision Awareness in.. @darl_icml
213 Followers 9 Following Decision Awareness in Reinforcement Learning Workshop @icmlconfJason Lee @jasondeanlee
10K Followers 3K Following Associate Professor at Princeton and Research Scientist at Google DeepMind. ML/AI Researcher working on foundations of LLMs and deep learningAndrea Montanari @Andrea__M
6K Followers 238 Following Professor, Statistics and Mathematics, Stanford University.Gergely Neu @neu_rips
9K Followers 667 Following ML theory nerd & AI non-enthusiast. thinking a lot about online learning these days!Alex Turner @Turn_Trout
1K Followers 39 Following Research scientist on the scalable alignment team at Google DeepMind. All views are my own.Geoffrey Irving @geoffreyirving
8K Followers 259 Following Research Director at the UK AI Safety Institute (AISI). Previously DeepMind, OpenAI, Google Brain, etc. @[email protected]Brendan O'Donoghue @bodonoghue85
3K Followers 1K Following Research scientist at @GoogleDeepMind, working on generative models, deep learning, RL. PhD from @stanford.Agility Robotics @agilityrobotics
20K Followers 2K Following Advancing manufacturing and logistics automation with the world's best human-centric robotics solution. #MadeForWork #DigitYunhao (Robin) Tang @robinphysics
994 Followers 611 Following @GoogleDeepMind; Prev @DeepMind @ColumbiaSumeet Singh @Sumeet_Robotics
424 Followers 165 Following Research scientist at Google Brain Robotics in NYC. All views are my own.Zheqing (Bill) Zhu @ZheqingZhu
804 Followers 199 Following Senior Staff Research Lead Manager, Head of Applied Reinforcement Learning, Meta AI. PhD@Stanford. Photographer in leisure time. Play some music as well.Vivek Ranjan Agnihotr.. @vivekagnihotri
966K Followers 459 Following Storyteller। Our Mothers are real Gods.Max Welling @wellingmax
33K Followers 432 FollowingTheKashmirFiles @KashmirFiles
43K Followers 5 Following A major feature film on the true story of the Kashmir Genocide. Directed by @vivekagnihotri #RightToJusticeAnupam Kher @AnupamPKher
20.5M Followers 247 Following Actor/Teacher/MotivationalSpeaker/UN Ambassador @HeForShe/Author/Padma Shri/PadmaBhushanPatrick van der Smagt @padsmagt
478 Followers 56 FollowingAfshin Oroojlooy @oroojlooy
176 Followers 637 Following A deep reinforcement learning enthusiastic @ OracleWe're super excited to announce our fifth Keynote Speaker: @svlevine, who'll be discussing "Reinforcement Learning in the Age of Foundation Models."
youtu.be/Cf2L_tPvYdg Delighted to share this video introducing our school, the newly founded Wadhwani School of Data Science & AI at @iitmadras - home to the new dept @DSAI_IITM and several exciting research centres @rbc_dsai_iitm @cerai_iitm @IBSE_IITM @ai4bharat
How can we learn a foundational world model directly from Internet-scale videos without any action annotations? @YugeTen, @ashrewards and @jparkerholder from @GoogleDeepMind's Open-Endedness Team are presenting "Genie: Generative Interactive Environments" at the @UCL_DARK Seminar…
Why do diffusion models use the U-Net architecture? Fascinatingly, the U-Net's encoder-decoder structure with long skip connections naturally encodes the belief propagation algorithm for hierarchical models. Explore more in this paper! arxiv.org/abs/2404.18444. .
Should you do research in a AI startup? Does it burn someone else's money and your equity? Or is it the key to success? If you do it, how do you manage it? Drawing on experiences at Xerox PARC, Amazon, Body Labs, & @meshcapade, I try to shed some light: medium.com/@black_51980/s…
Looking forward to my trip to London next week to talk about "From Deep Reinforcement Learning to LLM-based Agents: Perspectives on Current Research", starting at @ucl @ucl_DARK on Monday 29th. Trip details and event links in posts below.
(1/5) Want to hear my insights on the future of intelligent agents?💡 From April 29th to May 3rd, I will be presenting to some of London’s top AI institutions: @GoogleDeepMind @Huawei @ucl @KingsCollegeLon @QMUL @imperialcollege
Introducing the Instruction Hierarchy, our latest safety research to advance robustness for prompt injections and other ways of tricking LLMs into executing unsafe actions. More details: arxiv.org/abs/2404.13208
The first lecture of our @Stanford CS25 V4 Transformers course (cs25.stanford.edu) is now released! Check it out here: youtube.com/watch?v=fKMB5U…. We (the instructors) gave a brief intro and overview of the history of NLP, Transformers and how they work, and their impact. We…
New work on LLM Control Theory! We frame LLMs as discrete dynamical systems and study prompting through the lens of reachability and controllability. We even proved some theorems!! Joint work my fellow EngSci 2T2 @witkowski_cam, Dr. @Sz_Looi, advised by Prof. Matt Thomson 🚀
we open sourced our chat interface. github.com/cohere-ai/cohe…
I've written up my study group lectures on implementing Transformers in PyTorch into a blog series: Creating Transformers from Scratch: - Part 1: The Attention Mechanism benjaminwarner.dev/2023/07/01/att… - Part 2: The Rest of the Transformer benjaminwarner.dev/2023/07/28/res…
This is the best tutorial I've seen for fully understanding and implementing Transformers models. It includes a complete working implementation from scratch of all the key pieces, written in a way to make learning and understanding as easy as possible.
I've written up my study group lectures on implementing Transformers in PyTorch into a blog series: Creating Transformers from Scratch: - Part 1: The Attention Mechanism benjaminwarner.dev/2023/07/01/att… - Part 2: The Rest of the Transformer benjaminwarner.dev/2023/07/28/res…
We are open sourcing AIDE, a machine learning code generation agent. Simply describe the problem in natural language; the agent will begin experimenting on your local machine and then deliver the solution code. github.com/WecoAI/aideml
🤯📽️🏃Annoucning controllable video generation workshop at ICML2024! Super excited for speaker line up, and looking forward to seeing submissions exploring controllability in video generation. Submission deadline is 31st May AOE (but why wait till then if you can submit now?!)
We are pleased to announce the first *controllable video generation* workshop at @icmlconf 2024! 📽️📽️📽️ We welcome submissions that explore video generation via different modes of control (e.g. text, pose, action). Deadline: 31st May AOE Website: sites.google.com/corp/view/cvgi…
Announcing NeurIPS Preschool Track This year, we invite preschoolers to submit machine learning research papers.
🎮 Introducing the new and improved Policy-Guided Diffusion! Vastly more accurate trajectory generation than autoregressive models, with strong gains in offline RL performance! Plus a ton of new theory and results since our NeurIPS workshop paper... Check it out ⤵️
# explaining llm.c in layman terms Training Large Language Models (LLMs), like ChatGPT, involves a large amount of code and complexity. For example, a typical LLM training project might use the PyTorch deep learning library. PyTorch is quite complex because it implements a very…
Have you ever wanted to train LLMs in pure C without 245MB of PyTorch and 107MB of cPython? No? Well now you can! With llm.c: github.com/karpathy/llm.c To start, implements GPT-2 training on CPU/fp32 in only ~1,000 lines of clean code. It compiles and runs instantly, and exactly…
Thanks for the invite Joseph - looking forward to discussing Craftax and the future of RL environments!
"Craftax: The future of RL environments is JAX" @mitrma will be presenting Craftax, a crazy fast GPU implementation of Crafter and a new rougelike dungeon crawler version of it too! Join us Mon April 8 at Noon ET/5PM UK. DM me your email for an invite!
If you're interested in any type of RL research, you have to try end-to-end pure JAX. With all of these new libraries and features coming out, theres no better time to dive in. Great work! @scowardai @mcbeukman
🔧 Looking to easily develop RL novel autocurricula methods? ⚡ Want clean, blazingly fast, and readily-modifiable baselines? Presenting JaxUED: a simple and clean RL autocurricula library written in Jax!