view article Article **Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization** nvidia • Sep 23 • 73
ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming Image-Text-to-Text • 0.9B • Updated 2 days ago • 393 • 58
ColPali: Efficient Document Retrieval with Vision Language Models Paper • 2407.01449 • Published Jun 27, 2024 • 51
view article Article Distillation in 2026 (so far): which frontier models use it and how sergiopaniego • Jul 8 • 25
view article Article MOPD: how frontier labs merge RL experts into one model and how to do it using TRL sergiopaniego • 2 days ago • 21
Running on Zero Agents 23 Weight-Space-Programmed Qwen3.5-0.8B 🧠 23 Compare two LLMs' answers to a math problem
RikiyaT/Qwen3.5-0.8B-weight-space-programming Image-Text-to-Text • 0.9B • Updated 3 days ago • 1.97k • 102
Running on Zero MCP 7 MiniCPM-OCR vs Unlimited-OCR-2 📄 7 Side-by-side OCR, MiniCPM-OCR 1.0 vs Unlimited-OCR-2
EmbeddingGemma 2: Unified and Efficient Multimodal Representations Paper • 2610.37364 • Published 10 days ago • 35