TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis Paper • 2508.13618 • Published Aug 19 • 18
EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs Paper • 2509.09174 • Published Sep 11 • 61
CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling Paper • 2510.04204 • Published Oct 5 • 20
DentalGPT: Incentivizing Multimodal Complex Reasoning in Dentistry Paper • 2512.11558 • Published 13 days ago • 41