🚀 The World’s First Public Diffusion Model Leaderboard (CLIP Score + FID Benchmarks!) By ytmack7 • about 12 hours ago • 1
🤯 These Two Diffusion Models Are Too Similar (Ideogram vs. Google's Nano Banana) By ytmack7 • about 12 hours ago • 1
Gaia2 Leaderboard Update: New Models and New Observations By meta-agents-research-environments and 3 others • about 12 hours ago • 5
VR Forklift Simulation Data for RLHF - Skills Model and Indicators By Forklift-Simulator • about 15 hours ago • 2
🤖 Transformers — The architecture that knocked out all competition! ⚡🎯 By RDTvlokip • about 21 hours ago • 1
🤖 Transformers — L'architecture qui a mis KO toute la concurrence ! ⚡🎯 By RDTvlokip • about 21 hours ago • 1
CU-1 for Autonomous UI Agent Systems: An Open Alternative to Proprietary Solutions By paulml • 1 day ago • 11
Qwen3-Omni: Advanced Architecture and Marketing Technology Applications By Sri-Vigneshwar-DJ • 2 days ago • 1
Optimizing Mixture-of-Experts Training: A Cost-Effective, Two-Sided Approach By kshitijthakkar • 3 days ago
🌀 RoPE (Rotary Position Embedding) — When AI finally learns where it is! 📍✨ By RDTvlokip • 3 days ago • 1
🌀 RoPE (Rotary Position Embedding) — Quand l'IA apprend enfin où elle en est ! 📍✨ By RDTvlokip • 3 days ago • 1
When Does Reasoning Matter? Unpacking the Contribution of Reasoning to LLM Performance By Nicolas-BZRD and 1 other • 3 days ago • 10
How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons By sherryxychen • 3 days ago • 9