Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published 14 days ago • 93
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance Paper • 2511.13254 • Published Nov 17, 2025 • 140
One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models Paper • 2511.10629 • Published Nov 13, 2025 • 133