view post Post 130 I made fastText 4× faster on CPU! 🚀Introducing fastText-turbo:⚡ 4.1× faster on x86, 1.7× on Apple Silicon✅ Same models, same predictions (labels)✅ Drop-in replacement, no retraining neededHow it works:https://commonglot.github.io/blog/fasttext-turbo.htmlCode:https://github.com/CommonGlot/fasttext-turbo See translation 🔥 1 1 + Reply
StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs Paper • 2606.20527 • Published Jun 18 • 4
Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs Paper • 2606.16011 • Published Jun 14 • 4
Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs Paper • 2606.16011 • Published Jun 14 • 4
Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs Paper • 2606.16011 • Published Jun 14 • 4
MenuCraft: Interactive Menu System Design with Large Language Models Paper • 2303.04496 • Published Mar 8, 2023 • 1
GIRT-Model: Automated Generation of Issue Report Templates Paper • 2402.02632 • Published Feb 4, 2024 • 1
MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment Paper • 2410.05873 • Published Oct 8, 2024 • 3
CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs Paper • 2510.09871 • Published Oct 10, 2025 • 3
Insights from the ICLR Peer Review and Rebuttal Process Paper • 2511.15462 • Published Nov 19, 2025 • 7
GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts Paper • 2604.12978 • Published Apr 14 • 6
GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts Paper • 2604.12978 • Published Apr 14 • 6
GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts Paper • 2604.12978 • Published Apr 14 • 6
Insights from the ICLR Peer Review and Rebuttal Process Paper • 2511.15462 • Published Nov 19, 2025 • 7
CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs Paper • 2510.09871 • Published Oct 10, 2025 • 3