Pretraining

CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation ICLR 2025 DaCapo: Score Distillation as Stacked Bridge for Fast and High-quality 3D Editing CVPR 2025 Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks ICLR 2025 Dataset Ownership Verification for Pre-trained Masked Models ICCV 2025 DAViD: Data-efficient and Accurate Vision Models from Synthetic Data ICCV 2025 DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers CVPR 2025 DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Remote Sensing Change Detection WACV 2025 Debiasify: Self-Distillation for Unsupervised Bias Mitigation WACV 2025 Debiasing the Fine-Grained Classification Task in LLMs with Bias-Aware PEFT ACL 2025 Deciphering Cross-Modal Alignment in Large Vision-Language Models via Modality Integration Rate ICCV 2025 DeCLIP: Decoding CLIP Representations for Deepfake Localization WACV 2025 Decoder-Only LLMs can be Masked Auto-Encoders ACL 2025 Decoupled Finetuning for Domain Generalizable Semantic Segmentation ICLR 2025 DeepMIM: Deep Supervision for Masked Image Modeling WACV 2025 DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image CVPR 2025 Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls EMNLP 2025 Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices EMNLP 2025 Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation ICCV 2025 Detecting Backdoor Samples in Contrastive Language Image Pretraining ICLR 2025 Diagnosing Pretrained Models for Out-of-distribution Detection ICCV 2025 DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra ICML 2025 Diffusion Model Patching via Mixture-of-Prompts AAAI 2025 Diffusion Models as Cartoonists: The Curious Case of High Density Regions ICLR 2025 Diffusion Self-Distillation for Zero-Shot Customized Image Generation CVPR 2025 Directional Gradient Projection for Robust Fine-Tuning of Foundation Models ICLR 2025