iiinova — where your digital self keeps evolving

Reposted by Caglar Gulcehre

Epoch AI @epochai.bsky.social · 22/12/2025

We benchmarked several open-weight Chinese models on FrontierMath. Their top scores on Tiers 1-3 lag the overall frontier by about seven months.

183

Reposted by Caglar Gulcehre

Terence Tao @teorth.bsky.social · 08/08/2025

#IPAM (the institute for pure and applied mathematics) is facing a critical shortfall for operating expenses due to an unexpected suspension of NSF funding www.ipam.ucla.edu/news/nsf-fun... . Donations for emergency continuity of operations funding can be made at giving.ucla.edu/Campaign/Donat

ipam.ucla.edu

512539

Reposted by Caglar Gulcehre

Skander Moalla @skandermoalla.bsky.social · 15/07/2025

🚀 Big time! We can finally do simple LLM RL fine-tuning with rewards and leverage offline/off-policy data! ❌ You want rewards, but GRPO only works online? ❌ You want offline, but DPO is limited to preferences? ✅ QRPO can do both! 🧵Here's how we do it:

1124

Caglar Gulcehre @caglarai.bsky.social · 13/07/2025

We provide an efficient and performant method that provides best of both worlds in a new architecture. We managed to show that our approach scales better than the SOTA transformers with self-attention. Incredible execution and attention to details by @xiuyingwei.bsky.social !

040

Reposted by Caglar Gulcehre

Akhil Arora @akhilarora.bsky.social · 12/05/2025

Thrilled to announce that our work “Fleet of Agents” has been accepted @icmlconf.bsky.social. On average, FoA boosts quality by ~5% while reducing costs to ~40% of SOTA baselines. Blog post after the Neurips deadline ;) Until then: Paper: arxiv.org/abs/2405.066... Code: github.com/au-clan/FoA

1134

Reposted by Caglar Gulcehre

Anja Surina @anjasurina.bsky.social · 26/04/2025

Many thanks to all amazing collaborators that contributed to this project - Amin Mansouri, @lars-quaedvlieg.bsky.social , Amal Seddas, Maryna Viazovska, Emmanuel Abbe, @caglarai.bsky.social 12/12

132

Reposted by Caglar Gulcehre

Anja Surina @anjasurina.bsky.social · 26/04/2025

Excited to share our latest work on EvoTune, a novel method integrating LLM-guided evolutionary search and reinforcement learning to accelerate the discovery of algorithms! 1/12🧵

12010

Caglar Gulcehre @caglarai.bsky.social · 26/04/2025

Wohoo🥳 Thrilled to announce this paper 📢. We have shown that it is possible to significantly improve the FunSearch method with RL and achieve impressive algorithmic discoveries on challenging NP-complete combinatorial optimization tasks like TSP and bin-packing.

140

Reposted by Caglar Gulcehre

Akhil Arora @akhilarora.bsky.social · 24/03/2025

🚨🚨 24 more hours to register your abstracts for the @grades-nda.bsky.social workshop @sigmod2025.bsky.social Papers due March 30th 23:59 AoE 🚀 @sdumbrava.bsky.social @olafhartig.bsky.social @csaudk.bsky.social

051

Reposted by Caglar Gulcehre

Akhil Arora @akhilarora.bsky.social · 18/03/2025

I am recruiting 2 PhD students for Fall'25 @csaudk.bsky.social to work on bleeding-edge topics in #NLProc #LLMs #AIAgents (e.g. LLM reasoning, knowledge-seeking agents, and more). Details: www.cs.au.dk/~clan/openings Deadline: May 1, 2025 Please boost! cc: @aicentre.dk @wikiresearch.bsky.social

cs.au.dk

Open positions and projects

### Open semester and Master's projects If you're an AU student looking for a semester project, a Bachelor project, or an MS thesis project, please refer to [this list](projects). ### Prospective PhD ...

03022

Reposted by Caglar Gulcehre

Ethan Mollick @emollick.bsky.social · 09/03/2025

If it turns out LLMs are only capable of recombinatory innovation (finding novel connections among existing knowledge), that would still be very useful. Most innovation is recombination and one of the big issues in science is that fields are too vast for scientists to bridge them to find connections

1017116

Reposted by Caglar Gulcehre

Csaba Szepesvari @skiandsolve.bsky.social · 06/03/2025

www.youtube.com/watch?v=9_Pe... An interview with Rich. The humility of Rich is truly inspiring: "There are no authorities in science". I wish people would listen and live by this.

youtube.com

TURING AWARD WINNER Richard S. Sutton in Conversation with Cam Linke | No Authorities in Science

YouTube video by Amii

24013

Reposted by Caglar Gulcehre

kyunghyuncho.bsky.social @kyunghyuncho.bsky.social · 25/02/2025

stay tuned for more proper, detailed and exciting cover of this preprint, but whoa i'm so proud of the team @prescientdesign.bsky.social and our achievements on <Lab-in-the-loop therapeutic antibody design with deep learning>!

1205

Reposted by Caglar Gulcehre

George Takei @georgetakei.bsky.social · 22/02/2025

And I am an ally. If you are too, let the world know.

12827877917058

Caglar Gulcehre @caglarai.bsky.social · 18/02/2025

I have been using Glove80 kb in the last week due to my RSI and it improved significantly since then. But I am still baffled how hard it is to get used to a new kb layout. Oddly, although I type perfectly fine on it now, I can't enter my passwords with it because they are stored in my muscle memory.

020

Reposted by Caglar Gulcehre

Melanie Mitchell @melaniemitchell.bsky.social · 13/02/2025

Do large language models develop "emergent" models of the world? My latest Substack posts explore this claim and more generally the nature of "world models": LLMs and World Models, Part 1: aiguide.substack.com/p/llms-and-w... LLMs and World Models, Part 2: aiguide.substack.com/p/llms-and-w...

aiguide.substack.com

LLMs and World Models, Part 1

How do Large Language Models Make Sense of Their “Worlds”?

1421158

Reposted by Caglar Gulcehre

Jeff Dean @jeffdean.bsky.social · 09/02/2025

Trajan's (@starlord37.bsky.social) story & countless others like it in the face of these cuts and wild shifts in government fellowships intended for our brightest & most promising students will have long-term, deeply damaging effects on the U.S.'s competitiveness in science, math, CS and more.

25112

Reposted by Caglar Gulcehre

Jeff Dean @jeffdean.bsky.social · 22/01/2025

A great talk on the history and design decisions in Google's TPUs by my longtime colleague Norm Jouppi, winner of the 2024 Seymour Cray Computer Engineering award. Talk: www.youtube.com/watch?v=a-1x... Award announcement: www.computer.org/publications...

youtube.com

SC24 IEEE-CS Seymour Cray Computer Engineering Award

YouTube video by SC Conference Series

28613

Reposted by Caglar Gulcehre

Jeff Dean @jeffdean.bsky.social · 22/01/2025

We’ve been thrilled by the positive reception to Gemini 2.0 Flash Thinking we discussed in December. Today we’re sharing an experimental update w/improved performance on math, science, and multimodal reasoning benchmarks 📈: • AIME: 73.3% • GPQA: 74.2% • MMMU: 75.4%

815931

Reposted by Caglar Gulcehre

Sung Kim @sungkim.bsky.social · 13/01/2025

Google's Titans: a new architecture with attention and a meta in-context memory that learns how to memorize at test time as presented by one of the author - @alibehrouz.bsky.social

47018

Reposted by Caglar Gulcehre

Skander Moalla @skandermoalla.bsky.social · 10/12/2024

Also, check out our ML project template—it’s a game-changer!🚀🚀 @caglarai.bsky.social 🧑‍💻 github.com/CLAIRE-Labo/...

063

Reposted by Caglar Gulcehre

Skander Moalla @skandermoalla.bsky.social · 10/12/2024

Ever been puzzled by your PPO agent collapsing out of nowhere? 📈🤯📉 Come check out our poster tomorrow! Wed 11 Dec 11 am - 2 pm PST West Ballroom A-D #6403 @caglarai.bsky.social @andreamiele.bsky.social @razvan-pascanu.bsky.social

171

Caglar Gulcehre @caglarai.bsky.social · 09/12/2024

I am in Vancouver for NeurIPS 2024 until December 16th if you want to meet, DM or email me. We have two accepted papers from my lab: 1. Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers, on Wednesday, East Exhibit Hall A-C #2010 (1/3)

1114