Beyond Transcription: Mechanistic Interpretability in ASR
Paper • 2508.15882 • Published • 89
Gal Sarid
GalSarid
·
AI & ML interests
LLMs, SSMs, RAG systems, LLM based RAG systems
Sentiment-Analysis, Text based classifications
Organizations
upvoted a paper 9 months ago
upvoted a collection 10 months ago
upvoted an article 10 months ago
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
• • 777 upvoted an article 11 months ago
Article
Vision Language Models (Better, faster, stronger)
- +3
merve, sergiopaniego, ariG23498, pcuenq, andito
• • 613 upvoted 3
articles about 1 year ago
Article
Introducing HELMET: Holistically Evaluating Long-context Language Models
- +5
hyen, gaotianyu1350, houminmin, kding1, danf, moshew, cdq10131
• • 42 Article
Introduction to State Space Models (SSM)
lbourdois
• • 225 Article
Common AI Model Formats
ngxson
• • 72 upvoted an article over 1 year ago
Article
Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference
mfuntowicz, hlarcher
• • 76 upvoted an article almost 2 years ago
Article
Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding
- +9
ofirzaf, echarlaix, imargulis, danielkorat, jmamou, guybd, orenpereg, moshew, Haihao, aayasin, FanZhao
• • 9 upvoted a paper almost 2 years ago
upvoted an article about 2 years ago
Article
CPU Optimized Embeddings with 🤗 Optimum Intel and fastRAG
- +4
peterizsak, mber, danf, echarlaix, mfuntowicz, moshew
• • 14