{"total":127,"rows":[{"id":"2208.12262","title":"MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining","created":"2022-08-25","cited_by_count":187,"area":"distill"},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"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":"2311.12075","title":"BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning","created":"2023-11-20","cited_by_count":115,"area":"safety"},{"id":"2302.00864","title":"CLIPood: Generalizing CLIP to Out-of-Distributions","created":"2023-02-02","cited_by_count":96,"area":null},{"id":"2302.02503","title":"Leaving Reality to Imagination: Robust Classification via Generated Datasets","created":"2023-02-05","cited_by_count":91,"area":null},{"id":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","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":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71,"area":null},{"id":"2405.19716","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","created":"2024-05-30","cited_by_count":70,"area":"mllm"},{"id":"2303.03323","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","created":"2023-03-06","cited_by_count":63,"area":"safety"},{"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":"2305.19894","title":"Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias","created":"2023-05-31","cited_by_count":57,"area":"mllm"},{"id":"2303.17561","title":"SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger","created":"2023-03-30","cited_by_count":56,"area":"mllm"},{"id":"2310.02426","title":"EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods","created":"2023-10-03","cited_by_count":54,"area":"diffusion"},{"id":"2303.05952","title":"Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning","created":"2023-03-10","cited_by_count":53,"area":null},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"area":null},{"id":"2305.18287","title":"LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections","created":"2023-05-29","cited_by_count":43,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2406.11171","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","created":"2024-06-17","cited_by_count":42,"area":"mllm"},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2308.10045","title":"An Empirical Study of CLIP for Text-based Person Search","created":"2023-08-19","cited_by_count":38,"area":null},{"id":"2309.03406","title":"Distribution-Aware Prompt Tuning for Vision-Language Models","created":"2023-09-06","cited_by_count":35,"area":"mllm"},{"id":"2404.16033","title":"Cantor: Inspiring Multimodal Chain-of-Thought of MLLM","created":"2024-04-24","cited_by_count":34,"area":"lr"},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33,"area":null},{"id":"2303.06854","title":"Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor Attacks","created":"2023-03-13","cited_by_count":31,"area":"mllm"},{"id":"2212.04085","title":"Graph Matching with Bi-level Noisy Correspondence","created":"2022-12-08","cited_by_count":30,"area":null},{"id":"2305.14095","title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2310.00927","title":"Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP","created":"2023-10-02","cited_by_count":26,"area":null},{"id":"2405.18570","title":"It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap","created":"2024-05-28","cited_by_count":26,"area":null},{"id":"2305.11965","title":"Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization","created":"2023-05-19","cited_by_count":25,"area":null},{"id":"2403.12736","title":"Towards Multimodal In-Context Learning for Vision & Language Models","created":"2024-03-19","cited_by_count":25,"area":"mllm"},{"id":"2505.11528","title":"LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation","created":"2025-05-13","cited_by_count":24,"area":"wm"},{"id":"2406.03496","title":"Wings: Learning Multimodal LLMs without Text-only Forgetting","created":"2024-06-05","cited_by_count":23,"area":"mllm"},{"id":"2406.17639","title":"Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP","created":"2024-06-25","cited_by_count":23,"area":null},{"id":"2310.17468","title":"Cross-modal Active Complementary Learning with Self-refining Correspondence","created":"2023-10-26","cited_by_count":22,"area":null},{"id":"2408.06788","title":"Visual Neural Decoding via Improved Visual-EEG Semantic Consistency","created":"2024-08-13","cited_by_count":21,"area":null},{"id":"2211.09790","title":"ConStruct-VL: Data-Free Continual Structured VL Concepts Learning","created":"2022-11-17","cited_by_count":20,"area":null},{"id":"2212.03221","title":"ADIR: Adaptive Diffusion for Image Reconstruction","created":"2022-12-06","cited_by_count":20,"area":"diffusion"},{"id":"2305.08675","title":"Improved baselines for vision-language pre-training","created":"2023-05-15","cited_by_count":20,"area":"mllm"},{"id":"2310.05862","title":"Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks","created":"2023-10-05","cited_by_count":19,"area":"safety"},{"id":"2504.08896","title":"Position: Beyond Euclidean -- Foundation Models Should Embrace Non-Euclidean Geometries","created":"2025-04-11","cited_by_count":18,"area":null},{"id":"2504.12717","title":"Post-pre-training for Modality Alignment in Vision-Language Foundation Models","created":"2025-04-17","cited_by_count":18,"area":"mllm"},{"id":"2312.04554","title":"Improved Visual Grounding through Self-Consistent Explanations","created":"2023-12-07","cited_by_count":17,"area":null},{"id":"2210.05740","title":"Stochastic Constrained DRO with a Complexity Independent of Sample Size","created":"2022-10-11","cited_by_count":16,"area":null},{"id":"2303.16891","title":"Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations","created":"2023-03-29","cited_by_count":16,"area":"mllm"},{"id":"2403.10153","title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","created":"2024-03-15","cited_by_count":16,"area":null},{"id":"2304.10893","title":"FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval system","created":"2023-04-21","cited_by_count":15,"area":null},{"id":"2304.11619","title":"SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models","created":"2023-04-23","cited_by_count":15,"area":"mllm"},{"id":"2307.16617","title":"FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration","created":"2023-07-31","cited_by_count":13,"area":null},{"id":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2404.04575","title":"To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO","created":"2024-04-06","cited_by_count":11,"area":null},{"id":"2405.16996","title":"Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning","created":"2024-05-27","cited_by_count":10,"area":null},{"id":"2409.15968","title":"Adversarial Backdoor Defense in CLIP","created":"2024-09-24","cited_by_count":10,"area":"safety"},{"id":"2507.05113","title":"CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation","created":"2025-07-07","cited_by_count":10,"area":"safety"},{"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":"2404.09387","title":"RankCLIP: Ranking-Consistent Language-Image Pretraining","created":"2024-04-15","cited_by_count":9,"area":"mllm"},{"id":"2407.01445","title":"FastCLIP: A Suite of Optimization Techniques to Accelerate CLIP Training with Limited Resources","created":"2024-07-01","cited_by_count":9,"area":null},{"id":"2504.16801","title":"Decoupled Global-Local Alignment for Improving Compositional Understanding","created":"2025-04-23","cited_by_count":9,"area":"distill"},{"id":"2307.05906","title":"Mini-Batch Optimization of Contrastive Loss","created":"2023-07-12","cited_by_count":8,"area":null},{"id":"2309.06809","title":"TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification","created":"2023-09-13","cited_by_count":8,"area":null},{"id":"2310.03734","title":"Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency","created":"2023-10-05","cited_by_count":8,"area":null},{"id":"2407.13676","title":"Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2405.10286","title":"FFF: Fixing Flawed Foundations in contrastive pre-training results in very strong Vision-Language models","created":"2024-05-16","cited_by_count":7,"area":"mllm"},{"id":"2405.15728","title":"Disease-informed Adaptation of Vision-Language Models","created":"2024-05-24","cited_by_count":7,"area":"mllm"},{"id":"2405.17201","title":"Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View","created":"2024-05-27","cited_by_count":7,"area":"lr"},{"id":"2402.12613","title":"Analysis of Using Sigmoid Loss for Contrastive Learning","created":"2024-02-20","cited_by_count":6,"area":null},{"id":"2405.16417","title":"CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection","created":"2024-05-26","cited_by_count":6,"area":"mllm"},{"id":"2407.14007","title":"Multi-modal Relation Distillation for Unified 3D Representation Learning","created":"2024-07-19","cited_by_count":6,"area":null},{"id":"2409.09721","title":"Finetuning CLIP to Reason about Pairwise Differences","created":"2024-09-15","cited_by_count":6,"area":"lr"},{"id":"2412.06209","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2412.10761","title":"Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation","created":"2024-12-14","cited_by_count":5,"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":"2401.02137","title":"SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment","created":"2024-01-04","cited_by_count":4,"area":"mllm"},{"id":"2409.18372","title":"You Only Speak Once to See","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2411.15076","title":"RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistency","created":"2024-11-22","cited_by_count":4,"area":null},{"id":"2312.00674","title":"LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models","created":"2023-12-01","cited_by_count":3,"area":"mllm"},{"id":"2401.11633","title":"Zoom-shot: Fast and Efficient Unsupervised Zero-Shot Transfer of CLIP to Vision Encoders with Multimodal Loss","created":"2024-01-22","cited_by_count":3,"area":"mllm"},{"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":"2411.15099","title":"Context-Aware Multimodal Pretraining","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2311.14948","title":"Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective","created":"2023-11-25","cited_by_count":2,"area":"mllm"},{"id":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2408.16029","title":"Meta-Learn Unimodal Signals with Weak Supervision for Multimodal Sentiment Analysis","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2410.09156","title":"On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2503.01531","title":"Diversity Covariance-Aware Prompt Learning for Vision-Language Models","created":"2025-03-03","cited_by_count":2,"area":"mllm"},{"id":"2505.03174","title":"Automated Data Curation Using GPS & NLP to Generate Instruction-Action Pairs for Autonomous Vehicle Vision-Language Navigation Datasets","created":"2025-05-06","cited_by_count":2,"area":"driving"},{"id":"2505.15576","title":"Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models","created":"2025-05-21","cited_by_count":2,"area":"lr"},{"id":"2505.20152","title":"MMGeoLM: Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models","created":"2025-05-26","cited_by_count":2,"area":"mllm"},{"id":"2507.16296","title":"Cross-Modal Distillation For Widely Differing Modalities","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2510.15508","title":"Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2404.16365","title":"VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2410.16853","title":"Bridging the Modality Gap: Dimension Information Alignment and Sparse Spatial Constraint for Image-Text Matching","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2412.03093","title":"Expanding Event Modality Applications through a Robust CLIP-Based Encoder","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2412.07226","title":"Attention Head Purification: A New Perspective to Harness CLIP for Domain Generalization","created":"2024-12-10","cited_by_count":1,"area":null}],"next_cursor":"100"}