MLSP-P25.2

MOMENTUM-IMBUED LANGEVIN DYNAMICS (MILD) FOR FASTER SAMPLING

Nishanth Shetty, Manikanta Bandla, Nishit Neema, Indian Institute of Science, India; Siddarth Asokan, Microsoft Research Lab India (MSRI), India; Chandra Sekhar Seelamantula, Indian Institute of Science, India

Session:
MLSP-P25: Deep Generative Models III Poster

Track:
Machine Learning for Signal Processing

Location:
Poster Zone 3A
Poster Board PZ-3A.2

Presentation Time:
Thu, 18 Apr, 13:10 - 15:10 (UTC +9)

Session Chair:
Feng Yin, Chinese University of Hong Kong
View Manuscript
Presentation
Discussion
Resources
Session MLSP-P25
MLSP-P25.1: SYNTHESIZING Aβ-PET VIA AN IMAGE AND LABEL CONDITIONING LATENT DIFFUSION MODEL FOR DETECTING AMYLOID STATUS
Zaixin Ou, Yongsheng Pan, Yuanning Li, shanghaitech university, China; Fang Xie, Fudan University, China; Qihao Guo, Shanghai Jiao Tong University, China; Dinggang Shen, ShanghaiTech University, China
MLSP-P25.2: MOMENTUM-IMBUED LANGEVIN DYNAMICS (MILD) FOR FASTER SAMPLING
Nishanth Shetty, Manikanta Bandla, Nishit Neema, Indian Institute of Science, India; Siddarth Asokan, Microsoft Research Lab India (MSRI), India; Chandra Sekhar Seelamantula, Indian Institute of Science, India
MLSP-P25.3: PASTE AND HARMONIZE VIA DENOISING: SUBJECT-DRIVEN IMAGE EDITING WITH FROZEN PRE-TRAINED DIFFUSION MODEL
XIN ZHANG, JiaXian Guo, Paul Yoo, Yutaka Matsuo, Yusuke Iwasawa, The University of Tokyo, Japan
MLSP-P25.4: T-FOLEY: A CONTROLLABLE WAVEFORM-DOMAIN DIFFUSION MODEL FOR TEMPORAL-EVENT-GUIDED FOLEY SOUND SYNTHESIS
Yoonjin Chung, Junwon Lee, Juhan Nam, KAIST, Korea, Republic of
MLSP-P25.5: Audio-Journey: Open Domain Latent Diffusion Based Text-to-Audio Generation
Jackson Michaels, Northwestern University, United States of America; Juncheng Li, Laura Yao, Lijun Yu, Carnegie Mellon University, United States of America; Zach Wood-Doughty, Northwestern University, United States of America; Florian Metze, Carnegie Mellon University, United States of America
MLSP-P25.6: Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models
Emilian Postolache, Giorgio Mariani, Sapienza University of Rome, Italy; Luca Cosmo, Ca’ Foscari University of Venice, Italy; Emmanouil Benetos, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland; Emanuele Rodolà, Sapienza University of Rome, United Kingdom of Great Britain and Northern Ireland
MLSP-P25.7: A parameterized generative adversarial network using cyclic projection for explainable medical image classifications
Xiangyu Xiong, Yue Sun, Macao Polytechnic University, Macao; Xiaohong Liu, Shanghai Jiao Tong University, China; Chan-Tong Lam, Macao Polytechnic University, Macao; Tong Tong, Fuzhou University, China; Hao Chen, Jiangsu JITRI Sioux Technologies Co., Ltd, China; Qinquan Gao, Fuzhou University, China; Wei Ke, Tao Tan, Macao Polytechnic University, Macao
MLSP-P25.8: ON OPTIMIZING TIMESTEPS OF AN EDM BASED DIFFUSION SAMPLING PROCEDURE
Huiwen Luo, University of Technology Sydney, Australia; Guoqiang Zhang, University of Exeter, United Kingdom of Great Britain and Northern Ireland
MLSP-P25.9: ADVERSARIAL JAMMING FOR AUTOENCODER DISTRIBUTION MATCHING
Waleed El-Geresy, Deniz Gündüz, Imperial College London, United Kingdom of Great Britain and Northern Ireland
MLSP-P25.10: 2D Human Pose Estimation Calibration and Keypoint Visibility Classification
Zhongyu Jiang, Haorui Ji, Cheng-Yen Yang, Jenq-Neng Hwang, University of Washington, United States of America
MLSP-P25.11: GROUNDED-INSTRUCT-PIX2PIX: IMPROVING INSTRUCTION BASED IMAGE EDITING WITH AUTOMATIC TARGET GROUNDING
Artur Shagidanov, Hayk Poghosyan, Picsart AI Research, Armenia; Xinyu Gong, University of Texas at Austin, Picsart AI Research, United States of America; Zhangyang Wang, Picsart AI Research, University of Texas at Austin, United States of America; Shant Navasardyan, Picsart AI Research, United States of America; Humphrey Shi, Picsart AI Research, Georgia Tech, United States of America
MLSP-P25.12: MODELING THE IMPACT OF INTER-RATER DISAGREEMENT ON SLEEP STATISTICS USING DEEP GENERATIVE LEARNING
Hans van Gorp, Merel van Gilst, Pedro Fonseca, Sebastiaan Overeem, Ruud van Sloun, Eindhoven University of Technology, Netherlands
MLSP-P25.13: Closed-Loop Training for Projected GAN
Jiangwei Zhao, Liang Zhang, Lili Pan, Hongliang Li, University of Electronic Science and Technology of China, China
Contacts