Fabian Gloeckle
@fabiangloeckle.bsky.social
PhD student at FAIR at Meta and Ecole des Ponts with @syhw and @Amaury_Hayat, co-supervised by @wtgowers. Machine learning for mathematics and programming.
Reposted by Fabian Gloeckle
🔥Very happy to introduce BigO(Bench) dataset on @hf.co 🤗
✨3,105 coding problems and 1,190,250 solutions from CodeContests
✨Time/Space Complexity labels and curve coefficients
✨Up to 5k Runtime/Memory Footprint measures for each solution
huggingface.co/datasets/fac...
✨3,105 coding problems and 1,190,250 solutions from CodeContests
✨Time/Space Complexity labels and curve coefficients
✨Up to 5k Runtime/Memory Footprint measures for each solution
huggingface.co/datasets/fac...
April 3, 2025 at 2:46 PM
🔥Very happy to introduce BigO(Bench) dataset on @hf.co 🤗
✨3,105 coding problems and 1,190,250 solutions from CodeContests
✨Time/Space Complexity labels and curve coefficients
✨Up to 5k Runtime/Memory Footprint measures for each solution
huggingface.co/datasets/fac...
✨3,105 coding problems and 1,190,250 solutions from CodeContests
✨Time/Space Complexity labels and curve coefficients
✨Up to 5k Runtime/Memory Footprint measures for each solution
huggingface.co/datasets/fac...
February 6, 2025 at 1:05 PM
February 6, 2025 at 1:05 PM
The PyTorch reference transformer implementation for researchers. Amazing work!
x.com/mathuvu_/statu…
x.com/mathuvu_/statu…
February 6, 2025 at 1:05 PM
The PyTorch reference transformer implementation for researchers. Amazing work!
x.com/mathuvu_/statu…
x.com/mathuvu_/statu…
New generation of cross-lingual embedding models -- the same could work for code + math
x.com/JoaoMJaneiro/s…
x.com/JoaoMJaneiro/s…
February 6, 2025 at 1:05 PM
New generation of cross-lingual embedding models -- the same could work for code + math
x.com/JoaoMJaneiro/s…
x.com/JoaoMJaneiro/s…
February 6, 2025 at 1:04 PM
by @GuillaumeLample @tlacroix6 @MaLachaux @AurR0d @Amaury_Hayat @LavrilThibaut Gabriel Ebner @javier_m and others!
github.com/facebookresear…
github.com/facebookresear…
GitHub - facebookresearch/Evariste: HyperTree Proof Search for Neural Theorem Proving -- "La science est l'œuvre de l'esprit humain, qui est plutôt destiné à étudier qu'à connaître, à chercher qu'à trouver la vérité."
HyperTree Proof Search for Neural Theorem Proving -- "La science est l'œuvre de l'esprit humain, qui est plutôt destiné à étudier qu'à connaître, à chercher qu&...
github.com
February 6, 2025 at 1:04 PM
by @GuillaumeLample @tlacroix6 @MaLachaux @AurR0d @Amaury_Hayat @LavrilThibaut Gabriel Ebner @javier_m and others!
github.com/facebookresear…
github.com/facebookresear…
February 6, 2025 at 1:04 PM
#ICML Looking for recommendations for posters and orals on
- LM pretraining losses
- non-autoregressive architectures, energy-based architectures
- planning, subgoals, task decomposition
- ML for math and reasoning
Please shamelessly self-promote, promote others, comment or DM!
- LM pretraining losses
- non-autoregressive architectures, energy-based architectures
- planning, subgoals, task decomposition
- ML for math and reasoning
Please shamelessly self-promote, promote others, comment or DM!
February 6, 2025 at 1:04 PM
#ICML Looking for recommendations for posters and orals on
- LM pretraining losses
- non-autoregressive architectures, energy-based architectures
- planning, subgoals, task decomposition
- ML for math and reasoning
Please shamelessly self-promote, promote others, comment or DM!
- LM pretraining losses
- non-autoregressive architectures, energy-based architectures
- planning, subgoals, task decomposition
- ML for math and reasoning
Please shamelessly self-promote, promote others, comment or DM!
At #ICML this week to present Multi-token Prediction with @byoubii: poster session Wednesday 11.30 am - 1 pm Hall C 4-9 #915 - drop by to chat about pretraining losses with us!
icml.cc/virtual/2024/p…
icml.cc/virtual/2024/p…
ICML Poster Better & Faster Large Language Models via Multi-token Prediction
The ICML Logo above may be used on presentations. Right-click and choose
download. It is a vector graphic and may be used at any scale.
icml.cc
February 6, 2025 at 1:04 PM
At #ICML this week to present Multi-token Prediction with @byoubii: poster session Wednesday 11.30 am - 1 pm Hall C 4-9 #915 - drop by to chat about pretraining losses with us!
icml.cc/virtual/2024/p…
icml.cc/virtual/2024/p…
February 6, 2025 at 1:04 PM
February 6, 2025 at 1:04 PM
science starts in the appendix
February 6, 2025 at 1:04 PM
science starts in the appendix