{"total":98,"rows":[{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"2412.02856","title":"Is Large-Scale Pretraining the Secret to Good Domain Generalization?","created":"2024-12-03","cited_by_count":9,"area":null},{"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":"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":"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":"2310.09612","title":"Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations","created":"2023-10-14","cited_by_count":4,"area":null},{"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":"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":"2502.06209","title":"Enhancing Cost Efficiency in Active Learning with Candidate Set Query","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2308.03821","title":"Distributionally Robust Classification on a Data Budget","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2310.06622","title":"Robustness May be More Brittle than We Think under Different Degrees of Distribution Shifts","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2403.19669","title":"Analyzing the Roles of Language and Vision in Learning from Limited Data","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2405.17139","title":"Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling","created":"2024-05-27","cited_by_count":2,"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":"2403.07888","title":"Cross-modality debiasing: using language to mitigate sub-population shifts in imaging","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2405.17942","title":"Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2505.19990","title":"Progressive Scaling Visual Object Tracking","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.00903","title":"Leveraging CLIP Encoder for Multimodal Emotion Recognition","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2604.21104","title":"Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2606.06335","title":"Bridging Domain Expertise and Generalization for Performance Estimation","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2302.08973","title":"Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition","created":"2023-02-17","cited_by_count":0,"area":null},{"id":"2303.09608","title":"VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detection","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2305.08017","title":"How to Train Your CheXDragon: Training Chest X-Ray Models for Transfer to Novel Tasks and Healthcare Systems","created":"2023-05-13","cited_by_count":0,"area":null},{"id":"2311.13750","title":"Towards Transferable Multi-modal Perception Representation Learning for Autonomy: NeRF-Supervised Masked AutoEncoder","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2311.17949","title":"Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2401.10526","title":"On mitigating stability-plasticity dilemma in CLIP-guided image morphing via geodesic distillation loss","created":"2024-01-19","cited_by_count":0,"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":"2409.12076","title":"Unsupervised Domain Adaptation Via Data Pruning","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2502.20499","title":"Data Distributional Properties As Inductive Bias for Systematic Generalization","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2505.11895","title":"Adversarial Robustness for Unified Multi-Modal Encoders via Efficient Calibration","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2506.14607","title":"Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2512.14230","title":"Understanding the Gain from Data Filtering in Multimodal Contrastive Learning","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2605.29380","title":"TRACER: Persistent Regularization for Robust Multimodal Finetuning","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2608.06712","title":"Suppress and Diversify: Refining Robust Pathways for Corruption Robustness","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.13545","title":"LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.17700","title":"Environment-Invariant Subspace Learning for Generalizable Deepfake Detection","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2610.18871","title":"Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}