{"total":58,"rows":[{"id":"2307.15199","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","created":"2023-07-27","cited_by_count":59,"area":null},{"id":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57,"area":"mllm"},{"id":"2304.03916","title":"Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning","created":"2023-04-08","cited_by_count":47,"area":null},{"id":"2305.19164","title":"LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images","created":"2023-05-30","cited_by_count":46,"area":null},{"id":"2502.04263","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion","created":"2025-02-06","cited_by_count":43,"area":"mllm"},{"id":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36,"area":null},{"id":"2403.07241","title":"Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations","created":"2024-03-12","cited_by_count":30,"area":"mllm"},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2309.17430","title":"FACTS: First Amplify Correlations and Then Slice to Discover Bias","created":"2023-09-29","cited_by_count":26,"area":null},{"id":"2412.07909","title":"Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning","created":"2024-12-10","cited_by_count":26,"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":"2403.10153","title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","created":"2024-03-15","cited_by_count":16,"area":null},{"id":"2306.08893","title":"LOVM: Language-Only Vision Model Selection","created":"2023-06-15","cited_by_count":12,"area":"mllm"},{"id":"2310.16492","title":"On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection","created":"2023-10-25","cited_by_count":12,"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":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2307.14611","title":"TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation","created":"2023-07-27","cited_by_count":9,"area":null},{"id":"2503.09487","title":"Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness","created":"2025-03-12","cited_by_count":9,"area":null},{"id":"2402.03715","title":"Clarify: Improving Model Robustness With Natural Language Corrections","created":"2024-02-06","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":"2408.07832","title":"LADDER: Language-Driven Slice Discovery and Error Rectification in Vision Classifiers","created":"2024-07-31","cited_by_count":7,"area":null},{"id":"2503.08884","title":"SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs","created":"2025-03-11","cited_by_count":7,"area":"mllm"},{"id":"2403.19837","title":"Concept-based Analysis of Neural Networks via Vision-Language Models","created":"2024-03-28","cited_by_count":6,"area":"mllm"},{"id":"2410.01529","title":"Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning","created":"2024-10-02","cited_by_count":6,"area":null},{"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":"2601.18525","title":"Closing the Modality Gap Aligns Group-Wise Semantics","created":"2026-01-26","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":"2408.09570","title":"Say My Name: a Model's Bias Discovery Framework","created":"2024-08-18","cited_by_count":4,"area":null},{"id":"2410.06243","title":"Unsupervised Model Diagnosis","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2501.01109","title":"BatStyler: Advancing Multi-category Style Generation for Source-free Domain Generalization","created":"2025-01-02","cited_by_count":4,"area":null},{"id":"2412.07802","title":"Language Model as Visual Explainer","created":"2024-12-08","cited_by_count":3,"area":null},{"id":"2502.09564","title":"Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing","created":"2025-02-13","cited_by_count":3,"area":"diffusion"},{"id":"2503.17416","title":"Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study)","created":"2025-03-21","cited_by_count":3,"area":null},{"id":"2508.06092","title":"Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation","created":"2025-08-08","cited_by_count":3,"area":"mllm"},{"id":"2311.18291","title":"TLDR: Text Based Last-layer Retraining for Debiasing Image Classifiers","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2404.16717","title":"Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class","created":"2024-04-25","cited_by_count":2,"area":"mllm"},{"id":"2508.08570","title":"Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation","created":"2025-08-12","cited_by_count":2,"area":"mllm"},{"id":"2510.26302","title":"Understanding Hardness of Vision-Language Compositionality from A Token-level Causal Lens","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2511.00191","title":"A Retrospect to Multi-prompt Learning across Vision and Language","created":"2025-10-31","cited_by_count":2,"area":"mllm"},{"id":"2602.03098","title":"TextME: Bridging Unseen Modalities Through Text Descriptions","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2312.05588","title":"Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs","created":"2023-12-09","cited_by_count":1,"area":null},{"id":"2401.13213","title":"Common-Sense Bias Modeling for Classification Tasks","created":"2024-01-24","cited_by_count":1,"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":"2408.04955","title":"Model Debiasing by Learnable Data Augmentation","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2410.08478","title":"Federated Vision-Language-Recommendation with Personalized Fusion","created":"2024-10-11","cited_by_count":1,"area":"mllm"},{"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},{"id":"2505.11060","title":"CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2512.03463","title":"Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models","created":"2025-12-03","cited_by_count":1,"area":"mllm"},{"id":"2405.14030","title":"Refining Skewed Perceptions in Vision-Language Contrastive Models through Visual Representations","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2508.21761","title":"Learning from Silence and Noise for Visual Sound Source Localization","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2509.24431","title":"Semantic Compression via Multimodal Representation Learning","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2511.07897","title":"Data Descriptions from Large Language Models with Influence Estimation","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.13511","title":"Adapting MLLMs for Nuanced Video Retrieval","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2603.14610","title":"Make it SING: Analyzing Semantic Invariants in Classifiers","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.17246","title":"On the Cone Effect and Modality Gap in Medical Vision-Language Embeddings","created":"2026-03-18","cited_by_count":0,"area":"mllm"},{"id":"2603.17450","title":"VLM2Rec: Resolving Modality Collapse in Vision-Language Model Embedders for Multimodal Sequential Recommendation","created":"2026-03-18","cited_by_count":0,"area":"mllm"},{"id":"2605.29628","title":"COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings","created":"2026-05-28","cited_by_count":0,"area":null}],"next_cursor":null}