view article Article PangolinGuard: Fine-Tuning ModernBERT as a Lightweight Approach to AI Guardrails Mar 23, 2025 • 13
meta-llama/Llama-4-Maverick-17B-128E-Instruct Image-Text-to-Text • 402B • Updated May 22, 2025 • 30k • • 478
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 18 days ago • 866
DFlash Collection Block Diffusion for Flash Speculative Decoding • 14 items • Updated 3 days ago • 65
Can LLMs Learn to Reason Robustly under Noisy Supervision? Paper • 2604.03993 • Published 15 days ago • 42
The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning Paper • 2603.29025 • Published 20 days ago • 13
Meta-Harness: End-to-End Optimization of Model Harnesses Paper • 2603.28052 • Published 21 days ago • 18