{"total":21,"rows":[{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75,"area":null},{"id":"2305.13689","title":"Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training","created":"2023-05-23","cited_by_count":39,"area":null},{"id":"2212.06138","title":"CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet","created":"2022-12-12","cited_by_count":35,"area":null},{"id":"2309.00775","title":"Contrastive Feature Masking Open-Vocabulary Vision Transformer","created":"2023-09-02","cited_by_count":31,"area":null},{"id":"2305.15377","title":"Uncovering and Quantifying Social Biases in Code Generation","created":"2023-05-24","cited_by_count":25,"area":null},{"id":"2405.05237","title":"EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised Learning","created":"2024-05-08","cited_by_count":25,"area":null},{"id":"2211.12735","title":"Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migration","created":"2022-11-23","cited_by_count":24,"area":null},{"id":"2305.16233","title":"Interactive Segment Anything NeRF with Feature Imitation","created":"2023-05-25","cited_by_count":24,"area":null},{"id":"2402.02968","title":"Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives","created":"2024-02-05","cited_by_count":23,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2309.12042","title":"Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition","created":"2023-09-21","cited_by_count":10,"area":null},{"id":"2301.00230","title":"Disjoint Masking with Joint Distillation for Efficient Masked Image Modeling","created":"2022-12-31","cited_by_count":6,"area":null},{"id":"2305.16253","title":"Uncovering and Categorizing Social Biases in Text-to-SQL","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2303.10967","title":"Real-time 3D Semantic Scene Completion Via Feature Aggregation and Conditioned Prediction","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2306.07346","title":"Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2308.08884","title":"SRMAE: Masked Image Modeling for Scale-Invariant Deep Representations","created":"2023-08-17","cited_by_count":0,"area":null},{"id":"2312.04119","title":"A brief introduction to a framework named Multilevel Guidance-Exploration Network","created":"2023-12-07","cited_by_count":0,"area":null},{"id":"2603.29009","title":"MEDiC: Multi-objective Exploration of Distillation from CLIP","created":"2026-03-30","cited_by_count":0,"area":null}],"next_cursor":null}