Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published 11 days ago • 91
Trees from Marginals: Autoregressive drafting with factorized priors Paper • 2607.06763 • Published Jul 7 • 14
T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground Paper • 2512.10430 • Published Dec 11, 2025 • 121