Article
Getting More from Your Test-Time Compute Budget with Portfolio Beam Search
danelbaz
• • 8Oren Pereg
orenpereg
AI & ML interests
AI, NLP
Organizations
upvoted an article 3 months ago
upvoted an article 5 months ago
Article
DeepMath: A lightweight math reasoning Agent with smolagents
- +1
danf, mber, moshew
• • 40 upvoted an article 6 months ago
Article
Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models
- +3
imargulis, ofirzaf, sguskin, guybd, pcuenq
• • 25 upvoted an article 7 months ago
Article
SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit
- +4
ronenlap, tomaarsen, lewtun, danielkorat, orenpereg, moshew
• • 15 upvoted an article 8 months ago
Article
Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face
- +3
abidlabs, znation, nouamanetazi, sasha, qgallouedec
• • 223 upvoted a paper 9 months ago
upvoted 2
articles 11 months ago
Article
Training and Finetuning Sparse Embedding Models with Sentence Transformers
tomaarsen, arthurbresnu
• • 138 Article
The Transformers Library: standardizing model definitions
- +2
lysandre, ArthurZ, pcuenq, julien-c
• • 122 upvoted 4
articles about 1 year ago
Article
Introducing HELMET: Holistically Evaluating Long-context Language Models
- +5
hyen, gaotianyu1350, houminmin, kding1, danf, moshew, cdq10131
• • 42 Article
🚀 Accelerating LLM Inference with TGI on Intel Gaudi
- +3
baptistecolle, regisss, IlyasMoutawwakil, echarlaix, kding1
• • 14 Article
Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques
jmamou
• • 20 Article
From Zero to Reasoning Hero: How DeepSeek-R1 Leverages Reinforcement Learning to Master Complex Reasoning
NormalUhr
• • 17 upvoted 2
articles over 1 year ago
Article
SetFit: Efficient Few-Shot Learning Without Prompts
- +4
Unso, lewtun, luketheduke, danielkorat, orenpereg, moshew
• • 40 Article
Open-R1: a fully open reproduction of DeepSeek-R1
- +1
eliebak, lvwerra, lewtun
• • 889 upvoted a paper over 1 year ago
upvoted 2
articles over 1 year ago
Article
Understanding Mixtral-8x7b
vtabbott
• • 3 Article
Faster Assisted Generation with Dynamic Speculation
- +5
jmamou, orenpereg, joaogante, lewtun, danielkorat, Nadav-Timor, moshew
• • 51