MLSP-L27: Foundation and Generative Models for Multimodal Learning
Oral
Thu, 7 May, 16:30 - 18:30
Location: Room 117
Session Type: Oral
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview
Thu, 7 May, 16:30 - 16:50

MLSP-L27.1: REFINEBRIDGE: GENERATIVE BRIDGE MODELS IMPROVE FINANCIAL FORECASTING BY FOUNDATION MODELS
Anthony Bolton, Wuyang Zhou, Zehua Chen, Giorgos Iacovides, Danilo Mandic, Imperial College London, United Kingdom of Great Britain and Northern Ireland
Thu, 7 May, 16:50 - 17:10

MLSP-L27.2: IDEAvatar: Identity-Preserving Avatar Generation With Controllable Emotions
Tingyu Yuan, Chinese Academy of Sciences, University of Chinese Academy of Sciences, China; Kangxu Fan, Central South University, China; Wen Ye, Chinese Academy of Sciences, University of Chinese Academy of Sciences, China; Kaiwen Guo, Chinese Academy of Sciences, China; Biaoliang Guan, Kai Liu, Xi’an Jiaotong University, China; Chenchen Kong, Jie Li, Traffic Management Research Instituteof the Ministry of Public Security, China; Chaoyang Zhao, Chinese Academy of Sciences, objecteye.inc, China; Jinqiao Wang, Chinese Academy of Sciences, University of Chinese Academy of Sciences, China
Thu, 7 May, 17:10 - 17:30

MLSP-L27.3: MEM4TEETH: Memory-Guided Point Cloud Completion for Dental Reconstruction
Jianan Sun, Yukang Huang, Donghua University, China; Dongzhihan Wang, Shanghai University, China; Mingyu Fan, Donghua University, China
Thu, 7 May, 17:30 - 17:50

MLSP-L27.4: REFLECTIVE CONFIDENCE: CORRECTING REASONING FLAWS VIA ONLINE SELF-CORRECTION
Qinglin Zeng, Jing Yang, Keze Wang, Sun Yat-sen University, China
Thu, 7 May, 17:50 - 18:10

MLSP-L27.5: Scaling Spoken Language Models with Syllabic Speech Tokenization
Nicholas Lee, Cheol Jun Cho, UC Berkeley, United States of America; Alan W Black, Carnegie Mellon University, United States of America; Gopala K. Anumanchipalli, UC Berkeley, United States of America
Thu, 7 May, 18:10 - 18:30

MLSP-L27.6: MR-FLOWDPO: MULTI-REWARD DIRECT PREFERENCE OPTIMIZATION FOR FLOW-MATCHING TEXT-TO-MUSIC GENERATION
Alon Ziv, Meta MSL; The Hebrew University of Jerusalem, United States of America; Sanyuan Chen, Andros Tjandra, Meta MSL, United States of America; Yossi Adi, FAIR Team, Meta MSL; The Hebrew University of Jerusalem, Israel; Wei-Ning Hsu, Bowen Shi, Meta MSL, United States of America