Party is over: regularizing ColBERT models to fix efficient ANN methods
lightonai
• • 21
NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Party is over: regularizing ColBERT models to fix efficient ANN methods
lightonai
• • 21Intel XPU Kernel Skill: LLM-driven Triton kernel optimization for the Hugging Face Kernel Hub
danf
• • 10Introducing North Mini Code: Cohere’s First Model For Developers
CohereLabs
• • 73How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent
nvidia
• • 63QLORA SFT Distillation Effects on Qwen3.6 27B Agentic Coding Harness Fluency
bytkim
• • 8Introducing Serge: GitHub-Native AI Code Review
huggingface
• • 11No Photoshop, No Blender: Multimedia by Agent
mishig
• • 5V-Zero
hao05
• • 5Code a simple RAG from scratch
ngxson
• • 349KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 351How We Built OpenMythos: A Cybersecurity LLM Trained from Scratch
KingNish
• • 4The Office Meets Silicon Valley
build-small-hackathon
• • 6Enterprise AI benchmarks: head-to-head comparison of Falconer, Notion, Atlassian Rovo, Claude Code, and Codex
maxifalconer
• • 4From GRPO to DAPO and GSPO: What, Why, and How
NormalUhr
• • 127A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 30Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action
nvidia
• • 83PitchFight AI: Practice the Pitch Before the Real Room
prakhar811
• • 9Closet Twin: Your AI-Powered Personal Stylist Built for the Build Small Hackathon
build-small-hackathon
• • 4🧬 Carbon-VEPor: Efficient Variant Effect Prediction with Carbon
build-small-hackathon
• • 4Continuous batching for GRPO, now in TRL
sergiopaniego
• • 3