VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models Paper • 2609.32607 • Published 4 days ago • 53
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 1 day ago • 45
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 2 days ago • 210