Neural Networks

Holistic Tokenizer for Autoregressive Image Generation ICCV 2025 HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery ICCV 2025 HookMoE: A learnable performance compensation strategy of Mixture-of-Experts for LLM inference acceleration EMNLP 2025 HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts WACV 2025 HOPE for a Robust Parameterization of Long-memory State Space Models ICLR 2025 How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning ICLR 2025 How Feature Learning Can Improve Neural Scaling Laws ICLR 2025 How Gradient descent balances features: A dynamical analysis for two-layer neural networks ICLR 2025 How many samples are needed to train a deep neural network? ICLR 2025 How Not to Stitch Representations to Measure Similarity: Task Loss Matching Versus Direct Matching AAAI 2025 HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection AAAI 2025 HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly ICCV 2025 HUNet: Homotopy Unfolding Network for Image Compressive Sensing CVPR 2025 HVAdam: A Full-Dimension Adaptive Optimizer AAAI 2025 HWB-Net: A Novel High-Performance and Efficient Hybrid Waveform Bandwidth Extension Method Interspeech 2025 Hybrid Phenology Modeling for Predicting Temperature Effects on Tree Dormancy AAAI 2025 HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions AAAI 2025 Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation ICLR 2025 Hyperbolic Genome Embeddings ICLR 2025 HyperIV: Real-time Implied Volatility Smoothing ICML 2025 HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories CVPR 2025 HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks CVPR 2025 HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset CVPR 2025 HyTIP: Hybrid Temporal Information Propagation for Masked Conditional Residual Video Coding ICCV 2025 Identifying and Understanding Cross-Class Features in Adversarial Training ICML 2025