Pretraining

Distillation Scaling Laws ICML 2025 Distilling the Knowledge in Data Pruning ICML 2025 Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning ICLR 2025 DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID WACV 2025 Does Training with Synthetic Data Truly Protect Privacy? ICLR 2025 Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels ICCV 2025 Domain Generalization in CLIP via Learning with Diverse Text Prompts CVPR 2025 Domain Generalization using Large Pretrained Models with Mixture-of-Adapters WACV 2025 Don’t stop pretraining! Efficiently building specialised language models in resource-constrained settings. NAACL 2025 DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles CVPR 2025 DoubleDipper: Recycling Contexts for Efficient and Attributed In-Context Learning IJCNLP 2025 Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models ICCV 2025 DreamBlend: Advancing Personalized Fine-Tuning of Text-to-Image Diffusion Models WACV 2025 DreaMo: Articulated 3D Reconstruction from a Single Casual Video WACV 2025 Drop Dropout on Single Epoch Language Model Pretraining ACL 2025 Dual-Expert Consistency Model for Efficient and High-Quality Video Generation ICCV 2025 Duoduo CLIP: Efficient 3D Understanding with Multi-View Images ICLR 2025 dutir914 at SemEval-2025 Task 1: An integrated approach for Multimodal Idiomaticity Representations SemEval 2025 DV-Matcher: Deformation-based Non-rigid Point Cloud Matching Guided by Pre-trained Visual Features CVPR 2025 Each graph is a new language: Graph Learning with LLMs ACL 2025 EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild CVPR 2025 Edge Prompt Tuning for Graph Neural Networks ICLR 2025 EditCLIP: Representation Learning for Image Editing ICCV 2025 Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy ICCV 2025 Efficient and Microphone-Fault-Tolerant 3D Sound Source Localization Interspeech 2025