11 papers
LoopREG: Representation Supervision Enables Test-Time Recurrent Depth in Diffusion Transformers
Zipeng Wang, Anping Xiong, Jing Zhang +17
Reusing Transformer blocks offers a way to increase diffusion-model computation at test time, but naive recurrence can degrade generation beyond its training depth. We introduce Lo…
ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification
Jieyun Huang, Yi Shen, Kaikai Zhao +7
Fraudulent messages sent via Short Message Service (SMS) are increasingly obfuscated to evade cost-conscious classifiers in production systems. In Chinese SMS, attackers can exploi…
Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning
Ping Chen, Xiang Liu, Xingpeng Zhang +7
Diffusion models operate in a reflexive System 1 mode, constrained by a fixed, content-agnostic sampling schedule. This rigidity arises from the curse of state dimensionality, wher…
Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3D
Ping Chen, Zezhou Chen, Xingpeng Zhang +8
Current 2D-to-3D conversion methods achieve geometric accuracy but are artistically deficient, failing to replicate the immersive and emotionally resonant experience of professiona…
MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference
Huanlin Gao, Ping Chen, Fuyuan Shi +11
We present MeanCache, a training-free caching framework for efficient Flow Matching inference. Existing caching methods reduce redundant computation but typically rely on instantan…
LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation
Huanlin Gao, Ping Chen, Fuyuan Shi +5
We present LeMiCa, a training-free and efficient acceleration framework for diffusion-based video generation. While existing caching strategies primarily focus on reducing local he…
HiMo-CLIP: Modeling Semantic Hierarchy and Monotonicity in Vision-Language Alignment
Ruijia Wu, Ping Chen, Fei Shen +8
Contrastive vision-language models like CLIP have achieved impressive results in image-text retrieval by aligning image and text representations in a shared embedding space. Howeve…
PSTF-AttControl: Per-Subject-Tuning-Free Personalized Image Generation with Controllable Face Attributes
Xiang liu, Zhaoxiang Liu, Huan Hu +5
Recent advancements in personalized image generation have significantly improved facial identity preservation, particularly in fields such as entertainment and social media. Howeve…
Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity
Ping Chen, Xiang Liu, Zhaoxiang Liu +7
With the rapid advancement of large language models (LLMs), natural language processing (NLP) has achieved remarkable progress. Nonetheless, significant challenges remain in handli…
Hierarchical Deep Fusion Framework for Multi-dimensional Facial Forgery Detection -- The 2024 Global Deepfake Image Detection Challenge
Kohou Wang, Huan Hu, Xiang Liu +4
The proliferation of sophisticated deepfake technology poses significant challenges to digital security and authenticity. Detecting these forgeries, especially across a wide spectr…
Optimizing for the Shortest Path in Denoising Diffusion Model
Ping Chen, Xingpeng Zhang, Zhaoxiang Liu +6
In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality.…