Pretraining

QUESPA Submission for the IWSLT 2025 Dialectal and Low-resource Speech Translation Task ACL 2025 RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization ICLR 2025 RainbowPrompt: Diversity-Enhanced Prompt-Evolving for Continual Learning ICCV 2025 RandLoRA: Full rank parameter-efficient fine-tuning of large models ICLR 2025 Random Conditioning for Diffusion Model Compression with Distillation CVPR 2025 Ranking-aware adapter for text-driven image ordering with CLIP ICLR 2025 RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data ICLR 2025 Release the Powers of Prompt Tuning: Cross-Modality Prompt Transfer ICLR 2025 ReNovo: Retrieval-Based \emph{De Novo} Mass Spectrometry Peptide Sequencing ICLR 2025 REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers ICCV 2025 Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation CVPR 2025 Rethinking Personalized Aesthetics Assessment: Employing Physique Aesthetics Assessment as An Exemplification CVPR 2025 ReTracker: Exploring Image Matching for Robust Online Any Point Tracking ICCV 2025 Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization ICLR 2025 Retrieval Augmented Time Series Forecasting ICML 2025 Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning ICML 2025 Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation ICML 2025 Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts ICLR 2025 Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models ICLR 2025 Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets ICLR 2025 SAFT: Shape and Appearance of Fabrics from Template via Differentiable Physical Simulations from Monocular Video ICCV 2025 SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining CVPR 2025 SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation ICLR 2025 Scalable Data Synthesis through Human-like Cognitive Imitation and Data Recombination EMNLP 2025 Scalable Vision Language Model Training via High Quality Data Curation ACL 2025