Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Ming Gui
Computer Science > Computer Vision and Pattern Recognition
Learning representations that separate content and style is crucial for controllable generation and compositional generalization. However, diffusion and flow-based models trained primarily with generative objectives often produce entangled or misaligned factors. To address this gap, we introduce Contrastive Augmented Flow Matching (CAtFM), a framework that integrates contrastive regularization into an invertible flow matching formulation to promote structured content-style representations.
A DiT-style Mamba-based Diffusion Model
We present ZigMa, a scanning scheme that follows a zigzag pattern, considering both spatial continuity and parameter efficiency. We further adapt this scheme to video, separating the reasoning between spatial and temporal dimensions, thus achieving efficient parameter utilization. Our design allows for greater incorporation of inductive bias for non-1D data and improves parameter efficiency in diffusion models.
[2312.07360] Boosting Latent Diffusion with Flow Matching
[Submitted on 12 Dec 2023 ( v1 ), last revised 4 Dec 2024 (this version, v3)] Title:Boosting Latent Diffusion with Flow Matching View a PDF of the paper titled Boosting Latent Diffusion with Flow Matching, by Johannes Schusterbauer and Ming Gui and Pingchuan Ma and Nick Stracke and Stefan A. Baumann and Vincent Tao Hu and Bj\"orn Ommer View PDF HTML (experimental) Abstract:Visual synthesis has recently seen significant leaps in performance, largely due to breakthroughs in generative models.
Block-based Novel Haptic Data Reduction for Time-delayed Teleoperation
This work proposes a novel haptic data reduction scheme for time-delayed teleoperation by coding information as blocks. State-of-the-art (SOTA) haptic data reduction approaches are mainly sampled-based schemes. They encode haptic signals sample by sample in order to minimize the introduced coding delay. In contrast, our proposed block-based coding approach transmits a sample block as a single unit (haptic packet).
IRE1α‐mediated monounsaturated fatty acid synthesis drives B cell differentiation and lupus‐like autoimmune disease
FULL LENGTH Yana Zhang, Corresponding Author zhangyn95@mail.sysu.edu.cn Department of Otorhinolaryngology-Head and Neck Surgery, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, 510630 China Department of Pathology, Northwestern University Feinberg School of Medicine, 303 E.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Ming
Contact Ming, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack