← Techniques
Deep Learning › Techniques ›

Pretraining

2471 directly classified papers

Papers per year

Papers

Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP ICCV 2025
K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in Korean ACL 2025
DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image CVPR 2025
Video Language Model Pretraining with Spatio-temporal Masking CVPR 2025
Fine-tuning Whisper Tiny for Swahili ASR: Challenges and Recommendations for Low-Resource Speech Recognition ACL 2025
Memory-Efficient 4-bit Preconditioned Stochastic Optimization ICCV 2025
MDD: A Dataset for Text-and-Music Conditioned Duet Dance Generation ICCV 2025
SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models CVPR 2025
From Image to Video: An Empirical Study of Diffusion Representations ICCV 2025
Diagnosing Pretrained Models for Out-of-distribution Detection ICCV 2025
Debiasing the Fine-Grained Classification Task in LLMs with Bias-Aware PEFT ACL 2025
GASP: Gaussian Avatars with Synthetic Priors CVPR 2025
WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction ICCV 2025
Inference-Time Diffusion Model Distillation ICCV 2025
Boosting Vision Semantic Density with Anatomy Normality Modeling for Medical Vision-language Pre-training ICCV 2025
TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes ICCV 2025
Local Dense Logit Relations for Enhanced Knowledge Distillation ICCV 2025
MolHFCNet: Enhancing Molecular Graph Representations with Hierarchical Feature Combining and Hybrid Pretraining IJCAI 2025
DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers CVPR 2025
SfM-Free 3D Gaussian Splatting via Hierarchical Training CVPR 2025
Active Data Curation Effectively Distills Large-Scale Multimodal Models CVPR 2025
EgoM2P: Egocentric Multimodal Multitask Pretraining ICCV 2025
Rethinking Personalized Aesthetics Assessment: Employing Physique Aesthetics Assessment as An Exemplification CVPR 2025
Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices EMNLP 2025
Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation CVPR 2025