Submitted by philschmid 44 Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models DeepSeek 755 1
Submitted by Sylvestre 41 Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion ยท 6 authors 9 1
Submitted by zuom 16 Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages Bats Research 68 1