Caglar Gulcehre
@caglarml
Followers
5K
Following
6K
Media
40
Statuses
2K
Scientist, Prof @ EPFL, Ex-research scientist @ DeepMind, MSR, IBM Socials: https://t.co/qYmpvyUf0u, https://t.co/LZ5sWt7Asj
Lausanne, Switzerland
Joined July 2016
š¢I am thrilled to announce this paper. We showed 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.
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! 1/12š§µ
2
18
79
RT @docmilanfar: A surprising & little-known results in classical statistics:. Mean (Ī¼) and median (m) are within one std deviation:. |Ī¼ām|ā¦.
0
196
0
RT @umutsimsekli: Anyone from #iran looking for a phd/postdoc/research internship in statistical learning theory, deep learning theory etc,ā¦.
0
52
0
This is a very important work I believe if you are interested in AI safety and in particular on the AI control tax.
AI Control is a promising approach for mitigating misalignment risks, but will it be widely adopted? The answer depends on cost. Our new paper introduces the Control Taxāhow much does it cost to run the control protocols? (1/8) š§µ
0
1
9
RT @MiTerekhov: We did this work as part of the @MATSProgram. Very grateful to my amazing collaborators: Zhen Ning David Liu, @caglarml, @Sā¦.
0
1
0
RT @wendlerch: How do diffusion models create images and can we control that process? . We are excited to release a update to our SDXL Turbā¦.
0
18
0
RT @RichardHanania: Man comes to the US from Lebanon. Starts out delivering pizzas, becomes a Nobel winning neuroscientist. Trump freezes hā¦.
0
12K
0
RT @ellliottt: Call for Papers: . The 4th Annual Zurich Workshop in AI+Economics. to be held Dec 5-6, 2025, hosted by ETH Zurich and Univerā¦.
0
48
0
RT @shivamadarsh99: More details on the work with @JupyterAI @caglarml @nicholasmonath @mrinmayasachan .
0
1
0
RT @shivamadarsh99: I am happy to share that our work SIKeD has been accepted to ACL 2025 @aclmeeting findings! .More details below https:/ā¦.
0
2
0
RT @oguzhanthefatih: Happy to share that Iāve successfully defended my PhD thesis,.āScaling the Modalities in Multimodal Foundation Modelsāā¦.
0
9
0
It was fun to collaborate on this project.
Thrilled to announce that our work āFleet of Agentsā has been accepted @icmlconf. On average, FoA boosts quality by ~5% while reducing costs to ~40% of SOTA baselines. Blog post after the Neurips deadline ;).Until then:.Paper: Code:
1
0
10
RT @TaniaLombrozo: Accounts of learning typically focus on learning from external observations. But sometimes we learn without external inpā¦.
0
69
0
RT @keenanisalive: Jensen's inequality gives the difference between the average value of a convex function Ļ, and its value at the center,ā¦.
0
379
0
RT @SuryaGanguli: Many recent posts on free energy. Here is a summary from my class āStatistical mechanics of learning and computationā onā¦.
0
90
0
RT @random_walker: I tell students on the first day of class that if you're truly learning it's supposed to feel uncomfortable. The reasonā¦.
0
156
0