11 papers
Measured Sliders: Learning Continuous Controls from Differentiable Image Measurements
Yijia Chen, Boyu Wei, Xuanhua Yin
Continuous sliders are useful only when coefficient changes produce predictable image changes. Yet most diffusion sliders derive their axes from text or learned representations, le…
DefaultShift: Auditing Semantic Default Shift in Accelerated Text-to-Image Models
Xuanhua Yin, Chuanzhi Xu, Shunqi Mao +2
Few-step text-to-image models increasingly replace slower generators, yet acceleration can silently change distributions over unspecified attributes even when individual outputs re…
Calibrate What You SHIP: Post-Selection Risk Control for Verifier-Guided Text-to-Image Generation
Xuanhua Yin, Shunqi Mao, Wei Guo +2
Verifier-guided text-to-image systems increasingly use test-time search to select, refine, or stop among multiple candidates, yet release thresholds are often calibrated on individ…
Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancement
Chuanzhi Xu, Ziyuan Tao, Jean Julien KNell +5
Personalized image enhancement should reflect individual aesthetic taste, yet learning such preferences commonly depends on private photos and ratings that are unsuitable for centr…
SAFE-DiT: Semantics-Aware Fast-path Execution for High-Resolution Diffusion Transformers
Xuanhua Yin, Yuxuan Jia, Chuanzhi Xu +1
High-resolution Diffusion Transformer (DiT) inference contains substantial spatial redundancy, but many spatially adaptive implementations encode regional computation as attention…
Aes3D: Aesthetic Assessment in 3D Gaussian Splatting
Chuanzhi Xu, Boyu Wei, Haoxian Zhou +5
As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build m…
AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation
Xuanhua Yin, Chuanzhi Xu, Haoxian Zhou +2
Diffusion Transformers (DiTs) are a dominant backbone for high-fidelity text-to-image generation due to strong scalability and alignment at high resolutions. However, quadratic sel…
BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction
Xuanhua Yin, Runkai Zhao, Lina Yao +1
Naturalistic fMRI offers a time-resolved window into cortical dynamics during continuous multimodal experience, where future brain states are jointly governed by endogenous neural…
Improving Multimodal Brain Encoding Model with Dynamic Subject-awareness Routing
Xuanhua Yin, Runkai Zhao, Weidong Cai
Naturalistic fMRI encoding must handle multimodal inputs, shifting fusion styles, and pronounced inter-subject variability. We introduce AFIRE (Agnostic Framework for Multimodal fM…
Beyond Random Masking: A Dual-Stream Approach for Rotation-Invariant Point Cloud Masked Autoencoders
Xuanhua Yin, Dingxin Zhang, Yu Feng +3
Existing rotation-invariant point cloud masked autoencoders (MAE) rely on random masking strategies that overlook geometric structure and semantic coherence. Random masking treats…
HFBRI-MAE: Handcrafted Feature Based Rotation-Invariant Masked Autoencoder for 3D Point Cloud Analysis
Xuanhua Yin, Dingxin Zhang, Jianhui Yu +1
Self-supervised learning (SSL) has demonstrated remarkable success in 3D point cloud analysis, particularly through masked autoencoders (MAEs). However, existing MAE-based methods…