3 papers
cs.CL2026
EviDial: When Correct Depression Predictions Lack Evidence
Junjie Xu, Jin Zhu, Yuzhe Yang +6
Depression dialogue benchmarks commonly assess models by comparing predicted symptom labels with clinical scale scores. However, a prediction may agree with a benchmark label even…
cs.CV2024
Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation
Kaiyuan Liu, Jiahao Mei, Hengyu Zhang +3
Although Chinese calligraphy generation has achieved style transfer, generating calligraphy by specifying the calligrapher, font, and character style remains challenging. To addres…
cs.SD2024
TEAdapter: Supply abundant guidance for controllable text-to-music generation
Jialing Zou, Jiahao Mei, Xudong Nan +3
Although current text-guided music generation technology can cope with simple creative scenarios, achieving fine-grained control over individual text-modality conditions remains ch…