6 papers
Magnitude-Direction Decoupling for Fast Video Generation with Flow Matching Models
Haonan Xu, Feiyang Chen, Songkui Chen +5
Flow matching models for video generation achieve impressive performance but suffer from high computational overhead due to iterative denoising. In fact, the original model is not…
Shaping Parameter Contribution Patterns for Out-of-Distribution Detection
Haonan Xu, Yang Yang
Out-of-distribution (OOD) detection is a well-known challenge due to deep models often producing overconfident. In this paper, we reveal a key insight that trained classifiers tend…
LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents
Tianhao Zhao, Youjia Zhang, Hang Long +7
In this paper, we introduce LATO, a novel topology-preserving latent representation that enables scalable, flow matching-based synthesis of explicit 3D meshes. LATO represents a me…
Cross-Resolution Distribution Matching for Diffusion Distillation
Feiyang Chen, Hongpeng Pan, Haonan Xu +3
Diffusion distillation is central to accelerating image and video generation, yet existing methods are fundamentally limited by the denoising process, where step reduction has larg…
ITP: Instance-Aware Test Pruning for Out-of-Distribution Detection
Haonan Xu, Yang Yang
Out-of-distribution (OOD) detection is crucial for ensuring the reliable deployment of deep models in real-world scenarios. Recently, from the perspective of over-parameterization,…
Technical report on target classification in SAR track
Haonan Xu, Han Yinan, Haotian Si +1
This report proposes a robust method for classifying oceanic and atmospheric phenomena using synthetic aperture radar (SAR) imagery. Our proposed method leverages the powerful pre-…