MLSP-L32: Diffusion and Flow Models for Generative Learning
Oral
Fri, 8 May, 14:00 - 16:00
Location: Room 117
Session Type: Oral
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview
Fri, 8 May, 14:00 - 14:20

MLSP-L32.1: IMPROVING TEXT-INSTANCE ALIGNMENT OF FOREGROUND CONDITIONED OUT-PAINTING VIA CUSTOMIZED CONCEPT EMBEDDING
Yihao Zhao, Xuan Han, Bin He, Mingyu You, Tongji University, China
Fri, 8 May, 14:20 - 14:40

MLSP-L32.2: FONTMIMICKER: ENHANCING STYLIZED FONT GENERATION VIA FREQUENCY-AWARE DIFFUSION AND DEFORMABLE ALIGNMENT
Yihan Zhang, Yang Xue, South China University of Technology, China
Fri, 8 May, 14:40 - 15:00

MLSP-L32.3: QUADRATIC FLOW: CONSTANT ACCELERATION AS A PRIOR FOR LEARNING BETTER VELOCITY FIELD
Zhichao WU, Bo SUN, Jun He, Beijing Normal University, China
Fri, 8 May, 15:00 - 15:20

MLSP-L32.4: SMOGVLM: A SMALL, GRAPH-ENHANCED VISION-LANGUAGE MODEL
Debjyoti Mondal, Rituraj Singh, Subhadarshi Panda, Samsung R&D Institute India-Bangalore, India
Fri, 8 May, 15:20 - 15:40

MLSP-L32.5: CONTINUAL TIME SERIES FORECASTING WITH DIFFUSION MODELS UNDER FUNCTIONAL REGULARIZATION
Anand Ravishankar, Petar Djuric, Stony Brook University, United States of America
Fri, 8 May, 15:40 - 16:00

MLSP-L32.6: FLOWIID: SINGLE-STEP INTRINSIC IMAGE DECOMPOSITION VIA LATENT FLOW MATCHING
Mithlesh Singla, Seema Kumari, Shanmuganathan Raman, INDIAN INSTITUTE OF TECHNOLOGY GANDHINAGAR, India