Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation Paper • 2610.05608 • Published 20 days ago • 176
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs Paper • 2609.29845 • Published about 1 month ago • 105
Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published Sep 22 • 94
AdLoCo: adaptive batching significantly improves communications efficiency and convergence for Large Language Models Paper • 2508.18182 • Published Aug 25, 2025 • 2