The End of Manual Decoding: Towards Truly End-to-End Language Models Paper • 2510.26697 • Published 3 days ago • 92
Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations Paper • 2509.15655 • Published Sep 19 • 2
SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models Paper • 2509.15661 • Published Sep 19 • 2
Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges Paper • 2508.00454 • Published Aug 1 • 9