GigaChat Audio: Time-aware Large Audio Language Model Paper • 2607.10387 • Published 17 days ago • 36
GigaAM Multilingual: Foundation Model for Underrepresented Languages Paper • 2607.10371 • Published 17 days ago • 33
Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders Paper • 2606.10029 • Published Jun 8 • 12
Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success Paper • 2508.04280 • Published Aug 6, 2025 • 35
Train Sparse Autoencoders Efficiently by Utilizing Features Correlation Paper • 2505.22255 • Published May 28, 2025 • 24