Pattern Recognition

TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax.- Balancing Accuracy and Efficiency in Budget-Aware Early-Exiting Neural Networks.- An Evolutionary Search-Based Operator Fusion Method with Binary Representation for Deep Learning Inference Acceleration.- SemFaceEdit: Semantic Face Editing on Generative Radiance Manifolds.- (D^2)Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods.- Mask-ControlNet: Higher-Quality Image Generation with An Additional Mask Prompt.- Freestyle 3D-Aware Portrait Synthesis Based on Compositional Generative Priors.- FUGAN: A GAN Based Facial Reconstructor For Accurate Unveiling Of Hidden Faces.- Text2Street: Controllable Text-to-image Generation for Street Views.- Make An Image Move: Few-shot based Video Generation Guided by CLIP.- A Framework For Image Synthesis Using Supervised Contrastive Learning.- TMCSPEECH: A CHINESE TV AND MOVIE SPEECH DATASET WITH CHARACTER DESCRIPTIONS AND A CHARACTER-BASED VOICE GENERATION MODEL.- Deterministic Synthesis of Defect Images using Null Optimization.- Adaptive Refiner based Few-Shot Font Generation.- Controllable 3D object Generation with Single Image Prompt.- Beyond Labels: Aligning Large Language Models with Human-like Reasoning.- HindiLLM: Large Language Model for Hindi.- StableTalk: Advancing Audio-to-Talking Face Generation with Stable Diffusion And Vision Transformer.- Can LLMs perform structured graph reasoning tasks?.- Improved Zero-Shot Image Editing via Null-Toon and Directed Delta Denoising Score.- Texture  Spectral Decorrelation  Criteria.- A Low Rank Gaussian Mixture Latent Model for Face Generation.- Domain Adaptation for Machinery Fault Diagnosis Based on Critic Classifier GAN.- Data Augmentation Pipeline for Enhanced UAV Surveillance.- Generative Adversarial Networks for Imputing Sparse Learning Performance.- SWave: Improving Vocoder Efficiency by Straightening the Waveform Generation Path.- Outdoor Scene Relighting with Diffusion Models.- Matching aggregate posteriors in the variational autoencoder.- Efficient Nonlinear DAG Learning under Projection Framework.- GCompletor: A Graph-based Deep Learning Method for Traffic State Imputation on Urban Road Networks.