AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders Paper • 2602.05027 • Published Feb 4 • 63
Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLM Paper • 2512.21580 • Published Dec 25, 2025 • 8
Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian Paper • 2405.13929 • Published May 22, 2024 • 55
