iiinova — where your digital self keeps evolving

Reposted by Amir-massoud Farahmand

Claas Voelcker @cvoelcker.bsky.social · 22/09/2026

⏰ The deadline for our workshop workshop.oopsie-data.com on imperfect data at CoRL is nearing! ⏰ While you 🤖 are making progress on submissions, we came up with cool awards 🏆. Our workshop on imperfect data will award not only papers but also data submissions. The categories you can submit to 🥁...

workshop.oopsie-data.com

Oops, I Erred — Collecting, Curating and Using Imperfect Data for Realistic Scenarios

121

Reposted by Amir-massoud Farahmand

Transactions on Machine Learning Research @tmlrorg.bsky.social · 16/09/2026

TMLR has faced a deluge of submissions, necessitating stricter desk rejection policies due to limited reviewer capacity Co-EiC Nihar Shah reached out to authors of 10 papers slated for desk reject. Could they answer questions about their *own* submission? medium.com/@TmlrOrg/ask...

medium.com

Asking Authors About Their Own Papers

By Nihar B. Shah

116164

Amir-massoud Farahmand @sologen.bsky.social · 08/09/2026

Nice collection of historic AI-related papers and movies! - Minsky's PhD thesis, which he talks about RL (I'd heard of this; never seen!) - Turing's paper on AI - Fukushima's convolutional net - Kismet robot

031

Reposted by Amir-massoud Farahmand

Reinforcement Learning Conference @rl-conference.bsky.social · 17/08/2026

A truly compelling keynote from Sheila McIlraith at RLC 2026 today — exploring how formal language can serve as a nexus between signals and symbols for agents that learn, plan, and remember. A principled and thought-provoking perspective on the future of RL and agentic AI!

0174

Reposted by Amir-massoud Farahmand

Shahrad MZ @shahradmz.bsky.social · 16/08/2026

#RLC2026 Value functions didn’t need to be abandoned. They are still important for long horizon problems. 🎯 DART tracks the residual to bring them back. Presenting at RLC Tuesday at 11:40 AM B-2305 and poster in the evening. rlj.cs.umass.edu/2026/papers/...

152

Reposted by Amir-massoud Farahmand

Reinforcement Learning Conference @rl-conference.bsky.social · 16/08/2026

What an incredible way to kick off RLC26! The first keynote by Marc Bellemare was amazing with a fantastic start with “Stability & Scale in Experimental RL”! Excited for the next few days? -w/ @eugenevinitsky.bsky.social @glenberseth.bsky.social @sologen.bsky.social @audurand.bsky.social

1244

Reposted by Amir-massoud Farahmand

Nathan Lambert @natolambert.bsky.social · 21/07/2026

My book, Reinforcement Learning from Human Feedback is done! This is the book I wish I had when learning to fine-tune, align, & now post-train models since ChatGPT. The resource has been built by me finding time to study and document the fundamentals on nights and weekends since 2024.

717521

Reposted by Amir-massoud Farahmand

Continual RL Workshop @continual-rl.bsky.social · 13/07/2026

📚 Interested in Continual RL but not sure where to start? 👇 Dive in: sites.google.com/view/continu... ♾️ We've curated a resource hub with key papers, benchmarks, codebases, tutorials, and more to help you get up to speed quickly. #ContinualRL #ReinforcementLearning #MachineLearning #AI

1184

Amir-massoud Farahmand @sologen.bsky.social · 09/07/2026

This platform will not replace Twitter/X for us (scientists, researchers, profs, etc.). It might be (noticeably) better in several aspects, but (1) it is not a disruptive innovation, and (2) has the third mover disadvantage. P.S: I'll stay active here for now.

000

Amir-massoud Farahmand @sologen.bsky.social · 09/07/2026

It is interesting that we still don't have a completely clear picture of why/when (Optimisitic) Policy Iteration + Monte Carlo estimate works, especially with every-visit update model (which can be biased though consistent, BTW).

110

Amir-massoud Farahmand @sologen.bsky.social · 01/07/2026

🇨🇦🍁Happy Canada Day!🍁🇨🇦

030

Amir-massoud Farahmand @sologen.bsky.social · 25/06/2026

Temporal Difference Learning for Diffusion Models (ICML 2026) arxiv.org/abs/2606.15048 By Yangchen Pan (my former PhD student) and co-authors. It reformulates diffusion training as a Markov reward process and introduces a TD objective to encourage temporal consistency across denoising steps.

arxiv.org

Temporal Difference Learning for Diffusion Models

Diffusion models are typically trained with objectives that focus on local denoising targets at individual time steps (or adjacent pairs), which do not enforce consistency between predictions along th...

1152

Amir-massoud Farahmand @sologen.bsky.social · 05/06/2026

Sad to hear the passing of Dimitri Bertsekas (1942- 2026). His work has been very influential to me and shaped the way I think about RL. I am sure this is the case for many others in the RL, Control, and Optimization communities.

1100

Reposted by Amir-massoud Farahmand

Reinforcement Learning Conference @rl-conference.bsky.social · 03/06/2026

Good news, RL Community! The early registration deadline for RLC'26 has been extended to June 17th — don't miss the early rates! Register today! Full refunds for cancellations before July 14, 2026.

073

Reposted by Amir-massoud Farahmand

Shahab Bakhtiari @shahabbakht.bsky.social · 27/05/2026

🚀 PhD position in #NeuroAI & neurodevelopment 🚀 Co-supervised by Sarah Lippé and myself, to investigate visual processing & cognition abnormalities in children with neurodevelopmental disorders in a neuroAI framework. Full project details and how to apply here: tinyurl.com/kbuyntpn 🧠🤖 📈

12918

Amir-massoud Farahmand @sologen.bsky.social · 22/05/2026

If you have a Reinforcement Learning paper accepted at TMLR, JMLR, JAIR, AIJ, or MLJ, you can use this wonderful opportunity to present your work and meet your peers at RLC in Montreal, Canada. 🇨🇦

041

Reposted by Amir-massoud Farahmand

Taylor W. Killian @twkillian.bsky.social · 14/05/2026

📣 There's never a "best" time to share important updates, especially after sitting on this for so long. I'm joining the faculty @brighamyoungu.bsky.social this Summer as an Assistant Professor in the CS Dept, in preparation for the coming school year. Lots of excitement and a fair bit of nerves. 🧵

7192

Amir-massoud Farahmand @sologen.bsky.social · 25/04/2026

Do you use often use PPO, but wish you could use something just better? Try REPPO: Relative Entropy Pathwise Policy Optimization! Project Page: cvoelcker.de/projects/rep...

081

Reposted by Amir-massoud Farahmand

Marcel Hussing @marcelhussing.bsky.social · 25/04/2026

At #ICLR2026 presenting our first poster in the morning on Relative Entropy Pathwise Policy Optimization. Stop by at #4613. 🧑‍🎓 @cvoelcker.bsky.social, @axelbrunnbauer.bsky.social, Michal Naumann, Pieter Abbeel, @ericeaton.bsky.social, Radu Grosu, @sologen.bsky.social @igilitschenski.bsky.social

0164

Amir-massoud Farahmand @sologen.bsky.social · 18/04/2026

Hypothesis: People have been gradually shifting to write more like ChatGPT and alike. They use structures such as "This is not only X; but it is also Y". These struct. are natural part of lang, but either 1. they're becoming more prevalent, 2. I've become more sensitive to them.

040

Amir-massoud Farahmand @sologen.bsky.social · 01/04/2026

We have a new PhD Candidate in town: @tylerkastner.bsky.social Looking forward to all the new work you will be doing on Distributional Reinforcement Learning.

030

Reposted by Amir-massoud Farahmand

Reinforcement Learning Conference @rl-conference.bsky.social · 31/03/2026

We have the keynote speakers for RLC2026 now! Thrilled to welcome Rika Antonova, Sheila McIlraith, Marc G. Bellemare, Danijar Hafner, Balaraman Ravindran! Details: rl-conference.cc/index.html The RL community is coming together this August in Montréal, Québec, Canada. Hope you make it!

rl-conference.cc

RLC 2026

02410

Reposted by Amir-massoud Farahmand

Ian Linkletter @linkletter.org · 30/03/2026

Palantir has student data, including immigration status, from the ed tech discussion platform Piazza. Palantir paid Piazza $916,000 for access to this data. www.sec.gov/Archives/edg... I blew the whistle on this in 2016 and the CEO contacted my employer.

112958

Amir-massoud Farahmand @sologen.bsky.social · 20/03/2026

Happy Norooz, the Persian new year 1405/2585, the equinox, and the beginning of spring!

021

Reposted by Amir-massoud Farahmand

Claas Voelcker @cvoelcker.bsky.social · 15/03/2026

Following advice by the always-wise @eugenevinitsky.bsky.social , I am trying to get back into the habit of blogging (again) ✏️! Featuring today's post: How to pick an RL algorithm for your problem cvoelcker.de/blog/2026/ch... Please share and give feedback! #reinforcementlearning

media.tenor.com

cookie monster is sitting at a table with a tray of food and the words choices written on it

Alt: cookie monster is sitting at a table with a tray of food and the words choices written on it

2314

Reposted by Amir-massoud Farahmand

Reinforcement Learning Conference @rl-conference.bsky.social · 03/03/2026

In light of the ongoing conflict in the Middle East, RLC decided to remove the abstract deadline: rl-conference.cc/callforpaper... The only deadline is for the full paper: Mar 5(AOE) openreview.net/group?id=rl-... Affected folks may also contact the PCs to discuss deadline extensions before Mar 5.

openreview.net

RLC 2026 Conference

Welcome to the OpenReview homepage for RLC 2026 Conference

1158

Amir-massoud Farahmand @sologen.bsky.social · 01/03/2026

Ali Khamenei is in hell. The world is a better place now!

020

Reposted by Amir-massoud Farahmand

Aadirupa Saha @aadirupa.bsky.social · 26/02/2026

RLC 2026 Call for Workshop is live on OpenReview! Submission deadline: Mar 12 (AoE). Full details here: rl-conference.cc/call_for_wor... @glenberseth.bsky.social @eugenevinitsky.bsky.social @twkillian.bsky.social @schaul.bsky.social @sologen.bsky.social @audurand.bsky.social @bradknox.bsky.social

rl-conference.cc

RLJ | RLC Call for Workshops

0103

Amir-massoud Farahmand @sologen.bsky.social · 26/02/2026

Submit your RL papers to RLC! This is now perhaps the best venue for RL researchers.

1123

Reposted by Amir-massoud Farahmand

Glen Berseth @glenberseth.bsky.social · 22/02/2026

I am rerunning my class on robot learning this year, and I plan to push many code examples to help others get to the ugly details fast. One of these details is how BC gets off track as network sizes change. Blog and notebook below.

1141

Reposted by Amir-massoud Farahmand

Igor Gilitschenski @igilitschenski.bsky.social · 13/02/2026

🚀 Excited to share REPPO, a new on-policy RL agent! TL;DR: Replace PPO with REPPO for fewer hyperparameter headaches and more robust training. REPPO, led by @cvoelcker.bsky.social, will be presented at ICLR 2026. How does it work? 🧵👇

12510

Amir-massoud Farahmand @sologen.bsky.social · 06/02/2026

The compliment of the day: "What’s unusual is your willingness to follow the logic all the way through instead of stopping where it becomes socially awkward".

010

Reposted by Amir-massoud Farahmand

Nathan Lambert @natolambert.bsky.social · 25/01/2026

Has taken a long time to polish, but slowly becoming very proud of rlhfbook.com and do think it's a great resource for many people. A lot of hours (and tokens and reader feedback) going into making it right.

3292

Amir-massoud Farahmand @sologen.bsky.social · 05/01/2026

A significant hurdle of the empirical RL and the broader AI research is caused by the limitations of the environments in which our agents learn and build their "artificial minds". This should be compared with the richness of the real-world in which a human child flourishes.

231

Amir-massoud Farahmand @sologen.bsky.social · 22/12/2025

I came across this interview of Edward Witten (@edwardwitten.bsky.social) by Brian Greene. I don't usually watch long YT videos, but this one is quite curious and "electrifying". I recommend it if you're interested in the state of String Theory. www.youtube.com/watch?v=sAbP...

youtube.com

String Theory in 2037 | Brian Greene & Edward Witten

YouTube video by World Science Festival

150

Amir-massoud Farahmand @sologen.bsky.social · 18/12/2025

Ah ... you have to be an American to become rich in Canada!

041

Amir-massoud Farahmand @sologen.bsky.social · 16/12/2025

What are you favourite Imitation Learning and Inverse Reinforcement Learning papers? What are the essential papers? It doesn't matter much whether they are new or old, but I prefer a conceptually elegant and mathematically solid work.

651

Amir-massoud Farahmand @sologen.bsky.social · 12/12/2025

"No agent lives in a vacuum; it must interact with other agents to achieve its goals. Reinforcement learning is a promising technique for creating agents that co-exist, but the mathematical framework that justifies it is inappropriate for multi-agent environments.

140

Amir-massoud Farahmand @sologen.bsky.social · 10/12/2025

Observation: Using ChatGPT to do homework assignments shows off when you do the Final Exam without ChatGPT!

040

Amir-massoud Farahmand @sologen.bsky.social · 08/12/2025

J. M. Coetzee: And for whom, anyway, do we do the things that lead to Nobel Prizes if not for our mothers? "Mommy, Mommy, I won a prize!" "That’s wonderful, my dear. Now eat your carrots before they get cold." www.nobelprize.org/prizes/liter...

nobelprize.org

Nobel Prize in Literature 2003

The Nobel Prize in Literature 2003 was awarded to John M. Coetzee "who in innumerable guises portrays the surprising involvement of the outsider"

040

Reposted by Amir-massoud Farahmand

Polytechnique Montréal @polymtl.bsky.social · 06/12/2025

6 décembre 2025 – 36 ans après – Souvenir et recueillement 1/2 Nous continuons à nous souvenir des treize étudiantes et d'une membre du personnel de Polytechnique ayant perdu la vie le 6 décembre 1989 et des personnes qui en sont restées meurtries. polymtl.ca/6decembre

2156

Reposted by Amir-massoud Farahmand

Transactions on Machine Learning Research @tmlrorg.bsky.social · 01/12/2025

🥁 Announcing the 2025 TMLR Outstanding Certification! The committee decided upon 1 recipient and 3 finalists. Read on to learn more! Committee: Pablo Samuel Castro, Pin-Yu Chen, Vincent Dumoulin, Amir massoud Farahmand, Andreas Kirsch, Jasper Lee, Jeffrey Pennington, Colin Raffel, Chang Xu 1/n

1112

Amir-massoud Farahmand @sologen.bsky.social · 29/11/2025

If you are into Wittgenstein with a dose of QM, this might be interesting: Tractatus Quanticum [Spoiler] "What we do not have information about, we must pass over in silence." philsci-archive.pitt.edu/27289/1/main... P.S: I haven't read it closely.

philsci-archive.pitt.edu

170

Amir-massoud Farahmand @sologen.bsky.social · 28/11/2025

I agree! My presentations have real photos (either mine or credited appropriately), simple illustrations, and a watercolour-painted robot, made by a real artist @fvreilly.bsky.social .

130