Pretraining

Generative or Discriminative? Revisiting Text Classification in the Era of Transformers EMNLP 2025 Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation ICLR 2025 GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes ICCV 2025 Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data NAACL 2025 GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation ICCV 2025 GMAP: Generalized Manipulation of Articulated Objects in Robotic Using Pre-trained Model AAAI 2025 GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task ACL 2025 GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial Attacks ICLR 2025 GraphTranslate: Predicting Clinical Trial Translation using Graph Neural Networks on Biomedical Literature ACL 2025 GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models ACL 2025 GT-Mean Loss: A Simple Yet Effective Solution for Brightness Mismatch in Low-Light Image Enhancement ICCV 2025 Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment CVPR 2025 Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling ICCV 2025 HDR Image Generation via Gain Map Decomposed Diffusion ICCV 2025 Heavy Labels Out! Dataset Distillation with Label Space Lightening ICCV 2025 Heisenberg at BLP-2025 Task 1: Bangla Hate Speech Classification using Pretrained Language Models and Data Augmentation AACL 2025 HePa: Heterogeneous Graph Prompting for All-Level Classification Tasks AAAI 2025 HGAdapter: Hypergraph-based Adapters in Language Models for Code Summarization and Clone Detection EMNLP 2025 Hiding Images in Diffusion Models by Editing Learned Score Functions CVPR 2025 HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model ICCV 2025 Holographic Node Representations: Pre-training Task-Agnostic Node Embeddings ICLR 2025 How Does Critical Batch Size Scale in Pre-training? ICLR 2025 HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models ICCV 2025 HTU at SemEval-2025 Task 11: Divide and Conquer - Multi-Label emotion classification using 6 DziriBERTs submodels with Label-fused Iterative Mask Filling technique for low-resource data augmentation. SemEval 2025 H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models ICML 2025