Deep Learning

Preference-Oriented Supervised Fine-Tuning: Favoring Target Model over Aligned Large Language Models AAAI 2025 PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining ICCV 2025 Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison NAACL 2025 PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy ACL 2025 PresentAgent: Multimodal Agent for Presentation Video Generation EMNLP 2025 Preserve Anything: Controllable Image Synthesis with Object Preservation ICCV 2025 Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing CVPR 2025 Preserving Deep Representations in One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework ICLR 2025 Presto! Distilling Steps and Layers for Accelerating Music Generation ICLR 2025 Pretend Benign: A Stealthy Adversarial Attack by Exploiting Vulnerabilities in Cooperative Perception ICCV 2025 Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers EMNLP 2025 Pre-trained Models Perform the Best When Token Distributions Follow Zipf’s Law EMNLP 2025 Pre-Trained Multiple Latent Variable Generative Models are Good Defenders Against Adversarial Attacks WACV 2025 Pretrained Reversible Generation as Unsupervised Visual Representation Learning ICCV 2025 Pre-trained Semantic Interaction based Inductive Graph Neural Networks for Text Classification COLING 2025 Pre-Trained Vision-Language Models as Noisy Partial Annotators AAAI 2025 Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation AAAI 2025 Pre-training Auto-regressive Robotic Models with 4D Representations ICML 2025 Pretraining Context Compressor for Large Language Models with Embedding-Based Memory ACL 2025 Pre-Training Curriculum for Multi-Token Prediction in Language Models ACL 2025 Pre-training Distillation for Large Language Models: A Design Space Exploration ACL 2025 Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation ICML 2025 Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG ICML 2025 Pre-Training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck AAAI 2025 Pretraining Multi-Speaker Identification for Neural Speaker Diarization Interspeech 2025