Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published 8 days ago • 65
Running on Zero Agents 16 Universal Activation Oracle 🔮 16 Read LLM activations to detect bias, cross-model zero-shot
view article Article Borealis — open data, code, weights recipe for training Audio LLM AlexWortega • May 25 • 17
view article Article CircleGuardBench: New Standard for Evaluating AI Moderation Models whitecircle • May 7, 2025 • 59