{"total":138,"rows":[{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250,"area":null},{"id":"2303.07338","title":"Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need","created":"2023-03-13","cited_by_count":184,"area":null},{"id":"2311.18803","title":"BioCLIP: A Vision Foundation Model for the Tree of Life","created":"2023-11-30","cited_by_count":161,"area":null},{"id":"2501.04003","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","created":"2025-01-07","cited_by_count":122,"area":"mllm"},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119,"area":"mllm"},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2208.05516","title":"Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP","created":"2022-08-10","cited_by_count":97,"area":null},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2312.12359","title":"CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation","created":"2023-12-19","cited_by_count":96,"area":null},{"id":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93,"area":"mllm"},{"id":"2212.04825","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","created":"2022-12-09","cited_by_count":85,"area":null},{"id":"2302.14301","title":"A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking","created":"2023-02-28","cited_by_count":85,"area":null},{"id":"2406.18915","title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","created":"2024-06-27","cited_by_count":83,"area":"mllm"},{"id":"2404.07177","title":"Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic","created":"2024-04-10","cited_by_count":77,"area":"mllm"},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2407.16697","title":"AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarking","created":"2024-07-23","cited_by_count":65,"area":null},{"id":"2212.03241","title":"P{\\O}DA: Prompt-driven Zero-shot Domain Adaptation","created":"2022-12-06","cited_by_count":60,"area":null},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2209.00613","title":"ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets","created":"2022-09-01","cited_by_count":44,"area":null},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44,"area":null},{"id":"2307.03132","title":"T-MARS: Improving Visual Representations by Circumventing Text Feature Learning","created":"2023-07-06","cited_by_count":43,"area":null},{"id":"2405.17426","title":"Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving","created":"2024-05-27","cited_by_count":41,"area":null},{"id":"2207.07635","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning","created":"2022-07-15","cited_by_count":39,"area":null},{"id":"2403.11497","title":"A Sober Look at the Robustness of CLIPs to Spurious Features","created":"2024-03-18","cited_by_count":38,"area":"mllm"},{"id":"2310.09562","title":"Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?","created":"2023-10-14","cited_by_count":35,"area":null},{"id":"2211.08025","title":"FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers","created":"2022-11-15","cited_by_count":33,"area":null},{"id":"2211.16175","title":"Context-Aware Robust Fine-Tuning","created":"2022-11-29","cited_by_count":28,"area":null},{"id":"2311.17922","title":"A Simple Recipe for Language-guided Domain Generalized Segmentation","created":"2023-11-29","cited_by_count":28,"area":null},{"id":"2307.12532","title":"On the Connection between Pre-training Data Diversity and Fine-tuning Robustness","created":"2023-07-24","cited_by_count":25,"area":null},{"id":"2403.17381","title":"Application-Driven Innovation in Machine Learning","created":"2024-03-26","cited_by_count":24,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2311.18765","title":"MLLMs-Augmented Visual-Language Representation Learning","created":"2023-11-30","cited_by_count":21,"area":null},{"id":"2505.05528","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","created":"2025-05-08","cited_by_count":21,"area":"mllm"},{"id":"2402.07417","title":"An Empirical Study Into What Matters for Calibrating Vision-Language Models","created":"2024-02-12","cited_by_count":20,"area":"mllm"},{"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":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2302.13602","title":"The Role of Pre-training Data in Transfer Learning","created":"2023-02-27","cited_by_count":17,"area":null},{"id":"2411.09702","title":"On the Surprising Effectiveness of Attention Transfer for Vision Transformers","created":"2024-11-14","cited_by_count":17,"area":null},{"id":"2311.09191","title":"Domain Aligned CLIP for Few-shot Classification","created":"2023-11-15","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":"2402.05355","title":"A Survey on Safe Multi-Modal Learning System","created":"2024-02-08","cited_by_count":15,"area":null},{"id":"2501.11175","title":"ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models","created":"2025-01-19","cited_by_count":15,"area":"mllm"},{"id":"2306.16048","title":"Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity","created":"2023-06-28","cited_by_count":14,"area":"mllm"},{"id":"2510.11835","title":"Data or Language Supervision: What Makes CLIP Better than DINO?","created":"2025-10-13","cited_by_count":14,"area":"mllm"},{"id":"2302.01381","title":"Effective Robustness against Natural Distribution Shifts for Models with Different Training Data","created":"2023-02-02","cited_by_count":13,"area":null},{"id":"2304.06813","title":"Unified Out-Of-Distribution Detection: A Model-Specific Perspective","created":"2023-04-13","cited_by_count":13,"area":null},{"id":"2307.13136","title":"Does Progress On Object Recognition Benchmarks Improve Real-World Generalization?","created":"2023-07-24","cited_by_count":13,"area":null},{"id":"2308.13077","title":"Preserving Modality Structure Improves Multi-Modal Learning","created":"2023-08-24","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":"2407.05897","title":"Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models","created":"2024-07-08","cited_by_count":13,"area":null},{"id":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2306.08893","title":"LOVM: Language-Only Vision Model Selection","created":"2023-06-15","cited_by_count":12,"area":"mllm"},{"id":"2306.10191","title":"Neural Priming for Sample-Efficient Adaptation","created":"2023-06-16","cited_by_count":12,"area":null},{"id":"2407.16067","title":"LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomies","created":"2024-07-22","cited_by_count":12,"area":null},{"id":"2412.20392","title":"Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning","created":"2024-12-29","cited_by_count":12,"area":"safety"},{"id":"2312.10271","title":"Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Data","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2510.11653","title":"MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2210.03927","title":"APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations","created":"2022-10-08","cited_by_count":9,"area":null},{"id":"2306.15769","title":"What Makes ImageNet Look Unlike LAION","created":"2023-06-27","cited_by_count":9,"area":null},{"id":"2308.11194","title":"ViLLA: Fine-Grained Vision-Language Representation Learning from Real-World Data","created":"2023-08-22","cited_by_count":9,"area":"mllm"},{"id":"2310.08577","title":"Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models","created":"2023-10-12","cited_by_count":9,"area":"mllm"},{"id":"2311.01441","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","created":"2023-11-02","cited_by_count":9,"area":"mllm"},{"id":"2404.12139","title":"Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models","created":"2024-04-18","cited_by_count":9,"area":"mllm"},{"id":"2412.02856","title":"Is Large-Scale Pretraining the Secret to Good Domain Generalization?","created":"2024-12-03","cited_by_count":9,"area":null},{"id":"2502.09507","title":"When and How Does CLIP Enable Domain and Compositional Generalization?","created":"2025-02-13","cited_by_count":9,"area":"mllm"},{"id":"2305.06408","title":"Accelerating Batch Active Learning Using Continual Learning Techniques","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2301.07836","title":"Masked Autoencoding Does Not Help Natural Language Supervision at Scale","created":"2023-01-19","cited_by_count":7,"area":null},{"id":"2404.01542","title":"Predicting the Performance of Foundation Models via Agreement-on-the-Line","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2405.08911","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","created":"2024-05-14","cited_by_count":7,"area":null},{"id":"2310.13040","title":"Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2410.20406","title":"Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis","created":"2024-10-27","cited_by_count":6,"area":null},{"id":"2501.15377","title":"Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation","created":"2025-01-26","cited_by_count":6,"area":null},{"id":"2505.17810","title":"VIBE: Vector Index Benchmark for Embeddings","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2407.11121","title":"Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques","created":"2024-07-15","cited_by_count":5,"area":"mllm"},{"id":"2501.12535","title":"How Does the Spatial Distribution of Pre-training Data Affect Geospatial Foundation Models?","created":"2025-01-21","cited_by_count":5,"area":null},{"id":"2501.18936","title":"Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts","created":"2025-01-31","cited_by_count":5,"area":"moe"},{"id":"2503.05776","title":"FAA-CLIP: Federated Adversarial Adaptation of CLIP","created":"2025-02-26","cited_by_count":5,"area":"mllm"},{"id":"2512.00904","title":"Hierarchical Semantic Alignment for Image Clustering","created":"2025-11-30","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":"2210.07396","title":"Caption supervision enables robust learners","created":"2022-10-13","cited_by_count":4,"area":null},{"id":"2303.10937","title":"Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2310.04971","title":"Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift","created":"2023-10-08","cited_by_count":4,"area":null},{"id":"2310.07632","title":"Prompt Backdoors in Visual Prompt Learning","created":"2023-10-11","cited_by_count":4,"area":"safety"},{"id":"2310.09612","title":"Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations","created":"2023-10-14","cited_by_count":4,"area":null},{"id":"2602.06652","title":"Same Answer, Different Representations: Hidden instability in VLMs","created":"2026-02-06","cited_by_count":4,"area":"mllm"},{"id":"2304.04385","title":"On Robustness in Multimodal Learning","created":"2023-04-10","cited_by_count":3,"area":null},{"id":"2306.15692","title":"Utilizing Segment Anything Model For Assessing Localization of GRAD-CAM in Medical Imaging","created":"2023-06-24","cited_by_count":3,"area":null},{"id":"2406.03728","title":"Evaluating Durability: Benchmark Insights into Multimodal Watermarking","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2407.18658","title":"Adversarial Robustification via Text-to-Image Diffusion Models","created":"2024-07-26","cited_by_count":3,"area":"diffusion"},{"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":"2410.03140","title":"In-context Learning in Presence of Spurious Correlations","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2411.15099","title":"Context-Aware Multimodal Pretraining","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2501.18271","title":"Vision-Language Model Selection and Reuse for Downstream Adaptation","created":"2025-01-30","cited_by_count":3,"area":"mllm"},{"id":"2502.06209","title":"Enhancing Cost Efficiency in Active Learning with Candidate Set Query","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2507.06210","title":"CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions","created":"2025-07-08","cited_by_count":3,"area":"mllm"}],"next_cursor":"100"}