Article
MOPD: how frontier labs merge RL experts into one model and how to do it using TRL
sergiopaniego
• • 18
Ridha Chahed
ridha
AI & ML interests
ML
Recent Activity
upvoted a paper 5 days ago
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via
Reinforcement Learning upvoted an article 5 days ago
A brief history of distillation in AIOrganizations
upvoted an article 1 day ago
upvoted a paper 5 days ago
upvoted 2
articles 5 days ago
Article
A brief history of distillation in AI
sergiopaniego
• • 5 Article
Distillation in 2026 (so far): which frontier models use it and how
sergiopaniego
• • 25 upvoted an article 7 days ago
Article
A curriculum for post-training agents
huggingface
• • 101 upvoted a paper 2 months ago
upvoted an article 2 months ago
Article
How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code
nielsr
• • 34 upvoted a collection 7 months ago
upvoted 2
articles 8 months ago
Article
PRX Part 3 — Training a Text-to-Image Model in 24h!
Photoroom
• • 69 Article
Mixture of Experts (MoEs) in Transformers
- +5
ariG23498, pcuenq, merve, IlyasMoutawwakil, ArthurZ, sergiopaniego, Molbap
• • 182 upvoted an article 9 months ago
Article
Did GPT 5.2 make a breakthrough discovery in theoretical physics?
dlouapre
• • 63 upvoted an article 11 months ago
Article
Diffusers welcomes FLUX-2
- +6
YiYiXu, dg845, sayakpaul, OzzyGT, dn6, ariG23498, linoyts, multimodalart
• • 192 upvoted 4
articles about 1 year ago
Article
Scaling Test-Time Compute to Achieve Gold Medal at IOI 2025 with Open-Weight Models
nvidia
• • 19 Article
SmolLM3: smol, multilingual, long-context reasoner
- +21
eliebak, cmpatino, anton-l, edbeeching, m-ric, nouamanetazi, akseljoonas, guipenedo, hynky, clefourrier, SaylorTwift, kashif, qgallouedec, hlarcher, glutamatt, Xenova, reach-vb, ngxson, craffel, lewtun, loubnabnl, lvwerra, thomwolf
• • 805 Article
Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers
- +5
ariG23498, sergiopaniego, reach-vb, pcuenq, ArthurZ, SaylorTwift, cyrilvallez
• • 192 Article
Vision Language Model Alignment in TRL ⚡️
- +3
sergiopaniego, merve, qgallouedec, kashif, ariG23498
• • 115 upvoted an article over 1 year ago
Article
What is test-time compute and how to scale it?
Kseniase
• • 128 upvoted a paper over 1 year ago
upvoted an article over 1 year ago
Article
nanoVLM: The simplest repository to train your VLM in pure PyTorch
- +5
ariG23498, lusxvr, andito, sergiopaniego, merve, pcuenq, reach-vb
• • 265 upvoted a paper over 1 year ago