2 papers
cs.CL2026
Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models
Yizhong Geng, Yanliang Li, Jinghan Yang +4
Spoken Language Models (SLMs) have emerged as a promising paradigm for speech synthesis by bypassing explicit grapheme-to-phoneme pipelines. However, their effectiveness in low-res…
cs.CV2026
Discriminative Perception via Anchored Description for Reasoning Segmentation
Tao Yang, Qing Zhou, Yanliang Li +1
Reasoning segmentation increasingly employs reinforcement learning to generate explanatory reasoning chains that guide Multimodal Large Language Models. While these geometric rewar…