{"total":57,"rows":[{"id":"2506.18902","title":"jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval","created":"2025-06-23","cited_by_count":76,"area":null},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35,"area":"mllm"},{"id":"2602.17659","title":"When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs","created":"2026-02-19","cited_by_count":30,"area":"vla"},{"id":"2411.12785","title":"Joint Vision-Language Social Bias Removal for CLIP","created":"2024-11-19","cited_by_count":18,"area":null},{"id":"2508.04227","title":"Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting","created":"2025-08-06","cited_by_count":18,"area":"mllm"},{"id":"2502.10486","title":"VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap","created":"2025-02-14","cited_by_count":17,"area":"mllm"},{"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":"2511.16150","title":"Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval","created":"2025-11-20","cited_by_count":9,"area":"lr"},{"id":"2510.07115","title":"Enhancing Concept Localization in CLIP-based Concept Bottleneck Models","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2506.00037","title":"Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models","created":"2025-05-27","cited_by_count":5,"area":"rag"},{"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":"2502.14888","title":"Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models","created":"2025-02-16","cited_by_count":4,"area":"mllm"},{"id":"2505.19614","title":"Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2505.21524","title":"Learning Shared Representations from Unpaired Data","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2507.07985","title":"Common Data Properties Limit Object-Attribute Binding in CLIP","created":"2025-07-10","cited_by_count":4,"area":"mllm"},{"id":"2510.09473","title":"D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models","created":"2025-10-10","cited_by_count":3,"area":"mllm"},{"id":"2602.17395","title":"SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2603.13292","title":"Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs","created":"2026-02-28","cited_by_count":3,"area":"mllm"},{"id":"2603.19862","title":"IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment","created":"2026-03-20","cited_by_count":3,"area":"mllm"},{"id":"2503.03122","title":"The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models","created":"2025-03-05","cited_by_count":2,"area":"alignment"},{"id":"2601.14440","title":"VisTIRA: Closing the Image-Text Modality Gap in Visual Math Reasoning via Structured Tool Integration","created":"2026-01-20","cited_by_count":2,"area":"lr"},{"id":"2603.24528","title":"Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification","created":"2026-03-25","cited_by_count":2,"area":"mllm"},{"id":"2604.14684","title":"DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts","created":"2026-04-16","cited_by_count":2,"area":null},{"id":"2607.23052","title":"Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models","created":"2026-07-25","cited_by_count":2,"area":"mllm"},{"id":"2507.21291","title":"Fairness and Robustness of CLIP-Based Models for Chest X-rays","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2511.22141","title":"Bridging the Modality Gap by Similarity Standardization with Pseudo-Positive Samples","created":"2025-11-27","cited_by_count":1,"area":"mllm"},{"id":"2602.20046","title":"Closing the gap in multimodal medical representation alignment","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.15276","title":"Dataset Diversity Metrics and Impact on Classification Models","created":"2026-03-16","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":"2606.07451","title":"TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment","created":"2026-06-05","cited_by_count":1,"area":"mllm"},{"id":"2509.07936","title":"Feature Space Analysis by Guided Diffusion Model","created":"2025-09-09","cited_by_count":0,"area":"diffusion"},{"id":"2509.24431","title":"Semantic Compression via Multimodal Representation Learning","created":"2025-09-29","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":"2602.23906","title":"Half-Truths Break Similarity-Based Retrieval","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2604.00279","title":"The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2604.17822","title":"GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.03348","title":"Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts","created":"2026-05-05","cited_by_count":0,"area":"moe"},{"id":"2605.03456","title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.09352","title":"The Wittgensteinian Representation Hypothesis: Is Language the Attractor of Multimodal Convergence?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.26661","title":"Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models","created":"2026-05-26","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},{"id":"2605.30265","title":"LoMo: Local Modality Substitution for Deeper Vision-Language Fusion","created":"2026-05-28","cited_by_count":0,"area":"mllm"},{"id":"2606.17950","title":"Plug-and-Adapt: Multimodal Coreference Resolution at First Sight with a Pretrained Alignment Model","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.29888","title":"Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders","created":"2026-06-29","cited_by_count":0,"area":"mllm"},{"id":"2607.13805","title":"AspectCLIP: Optimizing CLIP Representation Space via Aspect-Guided Consistency Regularization","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.28640","title":"TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs","created":"2026-05-20","cited_by_count":0,"area":"mllm"},{"id":"2608.08418","title":"Learning Deep Modality-Shared Self-Expressiveness for Image Clustering with Textual Information","created":"2026-08-09","cited_by_count":0,"area":"mllm"},{"id":"2608.23634","title":"The Blending Ratio Is Not Where the Performance Is: Diagnosing Prototype Blending for Few-Shot Adaptation of Vision-Language Models","created":"2026-08-23","cited_by_count":0,"area":"mllm"},{"id":"2609.02663","title":"Characterizing Text Branch Sensitivity in Medical Vision-Language Segmentation via Evidence Decoupling","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.10224","title":"UOT-Gap: A Variational Principle for the Modality Gap in Vision-Language Models via Unbalanced Optimal Transport","created":"2026-09-09","cited_by_count":0,"area":"mllm"},{"id":"2609.17112","title":"Not Another Text Benchmark: Putting the \"Visual\" Back in Visual Question Answering for Large Video Models","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.33937","title":"Test-Time Generalized Category Discovery","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36101","title":"One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2609.39836","title":"Spherical Interpolation for Backward-Compatible Multimodal Representations","created":"2026-09-30","cited_by_count":0,"area":"mllm"},{"id":"2610.12907","title":"BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models","created":"2026-10-09","cited_by_count":0,"area":"mllm"},{"id":"2610.16135","title":"Omni-Modal LLMs Know More Than They Say","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}