{"total":139,"rows":[{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250,"area":null},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206,"area":null},{"id":"2502.02492","title":"VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models","created":"2025-02-04","cited_by_count":113,"area":null},{"id":"2408.04883","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","created":"2024-08-09","cited_by_count":111,"area":null},{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89,"area":null},{"id":"2406.08478","title":"What If We Recaption Billions of Web Images with LLaMA-3?","created":"2024-06-12","cited_by_count":87,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64,"area":null},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58,"area":null},{"id":"2505.05422","title":"TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation","created":"2025-05-08","cited_by_count":51,"area":null},{"id":"2405.15613","title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","created":"2024-05-24","cited_by_count":50,"area":null},{"id":"2509.18095","title":"MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction","created":"2025-09-22","cited_by_count":39,"area":null},{"id":"2404.18873","title":"OpenStreetView-5M: The Many Roads to Global Visual Geolocation","created":"2024-04-29","cited_by_count":38,"area":null},{"id":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2406.17711","title":"Data curation via joint example selection further accelerates multimodal learning","created":"2024-06-25","cited_by_count":33,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2403.18816","title":"Garment3DGen: 3D Garment Stylization and Texture Generation","created":"2024-03-27","cited_by_count":26,"area":null},{"id":"2509.26625","title":"Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training","created":"2025-09-30","cited_by_count":23,"area":null},{"id":"2507.14137","title":"Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning","created":"2025-07-18","cited_by_count":21,"area":null},{"id":"2406.05184","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","created":"2024-06-07","cited_by_count":19,"area":null},{"id":"2404.17507","title":"HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2504.14906","title":"OmniAudio: Generating Spatial Audio from 360-Degree Video","created":"2025-04-21","cited_by_count":17,"area":null},{"id":"2506.18851","title":"Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset","created":"2025-06-23","cited_by_count":17,"area":null},{"id":"2403.10153","title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","created":"2024-03-15","cited_by_count":16,"area":null},{"id":"2408.07221","title":"A Review of Pseudo-Labeling for Computer Vision","created":"2024-08-13","cited_by_count":16,"area":null},{"id":"2505.04601","title":"OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning","created":"2025-05-07","cited_by_count":16,"area":null},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2602.22394","title":"Vision Transformers Need More Than Registers","created":"2026-02-25","cited_by_count":15,"area":null},{"id":"2404.02900","title":"DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets","created":"2024-04-03","cited_by_count":14,"area":null},{"id":"2401.04716","title":"Low-Resource Vision Challenges for Foundation Models","created":"2024-01-09","cited_by_count":13,"area":null},{"id":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2504.02328","title":"Refining CLIP's Spatial Awareness: A Visual-Centric Perspective","created":"2025-04-03","cited_by_count":13,"area":null},{"id":"2510.10921","title":"FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model","created":"2025-10-13","cited_by_count":13,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2507.19054","title":"Closing the Modality Gap for Mixed Modality Search","created":"2025-07-25","cited_by_count":12,"area":null},{"id":"2509.24317","title":"Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2602.08683","title":"OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2411.08842","title":"AstroM$^3$: A self-supervised multimodal model for astronomy","created":"2024-11-13","cited_by_count":11,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2407.11784","title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2603.22387","title":"Efficient Universal Perception Encoder","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2502.09252","title":"On the Importance of Embedding Norms in Self-Supervised Learning","created":"2025-02-13","cited_by_count":9,"area":null},{"id":"2412.06235","title":"VariFace: Fair and Diverse Synthetic Dataset Generation for Face Recognition","created":"2024-12-09","cited_by_count":8,"area":null},{"id":"2506.04598","title":"Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets","created":"2025-06-05","cited_by_count":8,"area":null},{"id":"2508.18067","title":"Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images","created":"2025-08-25","cited_by_count":8,"area":null},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2408.04556","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","created":"2024-08-08","cited_by_count":7,"area":null},{"id":"2410.03478","title":"VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2503.06030","title":"Towards Universal Text-driven CT Image Segmentation","created":"2025-03-08","cited_by_count":7,"area":null},{"id":"2507.10095","title":"FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2509.01644","title":"OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning","created":"2025-09-01","cited_by_count":7,"area":null},{"id":"2602.01738","title":"Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models","created":"2026-02-02","cited_by_count":7,"area":null},{"id":"2311.17938","title":"Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitations","created":"2023-11-28","cited_by_count":6,"area":null},{"id":"2411.09126","title":"SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency","created":"2024-11-14","cited_by_count":6,"area":null},{"id":"2504.05253","title":"Contour Integration Underlies Human-Like Vision","created":"2025-04-07","cited_by_count":6,"area":null},{"id":"2510.04564","title":"Conditional Representation Learning for Customized Tasks","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2601.15369","title":"OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation","created":"2026-01-21","cited_by_count":5,"area":null},{"id":"2603.29080","title":"Is the Modality Gap a Bug or a Feature? A Robustness Perspective","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2402.02998","title":"Careful with that Scalpel: Improving Gradient Surgery with an EMA","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2406.04898","title":"Labeled Data Selection for Category Discovery","created":"2024-06-07","cited_by_count":4,"area":null},{"id":"2410.18472","title":"What If the Input is Expanded in OOD Detection?","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2504.08368","title":"FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2506.08887","title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2506.11389","title":"Curriculum-Guided Layer Scaling for Language Model Pretraining","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2508.04211","title":"What Holds Back Open-Vocabulary Segmentation?","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2511.13993","title":"Learning Skill-Attributes for Transferable Assessment in Video","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2502.03950","title":"LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models","created":"2025-02-06","cited_by_count":3,"area":null},{"id":"2502.16841","title":"Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2503.08805","title":"Filter Like You Test: Data-Driven Data Filtering for CLIP Pretraining","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2504.01792","title":"UniViTAR: Unified Vision Transformer with Native Resolution","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2507.09008","title":"VISTA: A Visual Analytics Framework to Enhance Foundation Model-Generated Data Labels","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2508.03091","title":"T2UE: Generating Unlearnable Examples from Text Descriptions","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2511.08417","title":"NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2602.05729","title":"Adaptive Global and Fine-Grained Perceptual Fusion for MLLM Embeddings Compatible with Hard Negative Amplification","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2410.07173","title":"Better Language Models Exhibit Higher Visual Alignment","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2411.19757","title":"Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models","created":"2024-11-29","cited_by_count":2,"area":null},{"id":"2502.06818","title":"Rethinking the Global Knowledge of CLIP in Training-Free Open-Vocabulary Semantic Segmentation","created":"2025-02-05","cited_by_count":2,"area":null},{"id":"2506.05027","title":"Tuning the Right Foundation Models is What you Need for Partial Label Learning","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2508.14197","title":"CLIPSym: Delving into Symmetry Detection with CLIP","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2508.16225","title":"An Investigation of Visual Foundation Models Robustness","created":"2025-08-22","cited_by_count":2,"area":null},{"id":"2603.04803","title":"Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2605.03245","title":"Text-Conditional JEPA for Learning Semantically Rich Visual Representations","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2405.18405","title":"WIDIn: Wording Image for Domain-Invariant Representation in Single-Source Domain Generalization","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2407.03463","title":"Precision at Scale: Domain-Specific Datasets On-Demand","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2409.13513","title":"Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2410.04751","title":"Intriguing Properties of Large Language and Vision Models","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2501.15955","title":"Rethinking the Bias of Foundation Model under Long-tailed Distribution","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2503.17110","title":"Beyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2504.07567","title":"Benchmarking Image Embeddings for E-Commerce: Evaluating Off-the Shelf Foundation Models, Fine-Tuning Strategies and Practical Trade-offs","created":"2025-04-10","cited_by_count":1,"area":null},{"id":"2507.00334","title":"Populate-A-Scene: Affordance-Aware Human Video Generation","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2510.06820","title":"Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2511.01593","title":"Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2603.00173","title":"Summer-22B: A Systematic Approach to Dataset Engineering and Training at Scale for Video Foundation Model","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2606.19584","title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2607.07673","title":"MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2408.15065","title":"The Benefits of Balance: From Information Projections to Variance Reduction","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2411.11162","title":"RPN 2: On Interdependence Function Learning Towards Unifying and Advancing CNN, RNN, GNN, and Transformer","created":"2024-11-17","cited_by_count":0,"area":null},{"id":"2503.21721","title":"Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fr\\'{e}chet Distance","created":"2025-03-27","cited_by_count":0,"area":null}],"next_cursor":"100"}