{"total":103,"rows":[{"id":"2407.12580","title":"E5-V: Universal Embeddings with Multimodal Large Language Models","created":"2024-07-17","cited_by_count":126,"area":"mllm"},{"id":"2403.19651","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","created":"2024-03-28","cited_by_count":119,"area":null},{"id":"2402.15116","title":"Large Multimodal Agents: A Survey","created":"2024-02-23","cited_by_count":105,"area":"lr"},{"id":"2412.14475","title":"MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval","created":"2024-12-19","cited_by_count":84,"area":"synth"},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"area":"mllm"},{"id":"2403.14599","title":"MyVLM: Personalizing VLMs for User-Specific Queries","created":"2024-03-21","cited_by_count":58,"area":"mllm"},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42,"area":null},{"id":"2412.11077","title":"Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval","created":"2024-12-15","cited_by_count":32,"area":"lr"},{"id":"2410.03659","title":"Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models","created":"2024-10-04","cited_by_count":28,"area":"mllm"},{"id":"2406.03411","title":"Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach","created":"2024-06-05","cited_by_count":25,"area":null},{"id":"2405.02951","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","created":"2024-05-05","cited_by_count":24,"area":null},{"id":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","cited_by_count":21,"area":null},{"id":"2503.19910","title":"CoLLM: A Large Language Model for Composed Image Retrieval","created":"2025-03-25","cited_by_count":21,"area":null},{"id":"2411.16752","title":"Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy","created":"2024-11-24","cited_by_count":18,"area":null},{"id":"2503.17109","title":"Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval","created":"2025-03-21","cited_by_count":18,"area":"wm"},{"id":"2502.18495","title":"A Comprehensive Survey on Composed Image Retrieval","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2502.20826","title":"CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image Retrieval","created":"2025-02-28","cited_by_count":16,"area":"lr"},{"id":"2311.07622","title":"Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval","created":"2023-11-13","cited_by_count":14,"area":"mllm"},{"id":"2405.15587","title":"Composed Image Retrieval for Remote Sensing","created":"2024-05-24","cited_by_count":14,"area":null},{"id":"2412.06014","title":"Post-hoc Probabilistic Vision-Language Models","created":"2024-12-08","cited_by_count":13,"area":"mllm"},{"id":"2412.11087","title":"Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image Retrieval","created":"2024-12-15","cited_by_count":13,"area":"mllm"},{"id":"2409.04918","title":"Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity","created":"2024-09-07","cited_by_count":12,"area":null},{"id":"2503.10166","title":"ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning","created":"2025-03-13","cited_by_count":12,"area":"mllm"},{"id":"2510.25387","title":"Instance-Level Composed Image Retrieval","created":"2025-10-29","cited_by_count":12,"area":null},{"id":"2412.16156","title":"Personalized Representation from Personalized Generation","created":"2024-12-20","cited_by_count":9,"area":null},{"id":"2407.05795","title":"HyCIR: Boosting Zero-Shot Composed Image Retrieval with Synthetic Labels","created":"2024-07-08","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":"2505.19952","title":"Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2410.05217","title":"Organizing Unstructured Image Collections using Natural Language","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2505.20764","title":"ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval","created":"2025-05-27","cited_by_count":7,"area":null},{"id":"2404.16193","title":"Improving Multi-label Recognition using Class Co-Occurrence Probabilities","created":"2024-04-24","cited_by_count":6,"area":null},{"id":"2502.20008","title":"Joint Fusion and Encoding: Advancing Multimodal Retrieval from the Ground Up","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2508.14039","title":"Beyond Simple Edits: Composed Video Retrieval with Dense Modifications","created":"2025-08-19","cited_by_count":6,"area":null},{"id":"2409.05405","title":"A Survey of Multimodal Composite Editing and Retrieval","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2505.15877","title":"Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2505.19707","title":"MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2407.06001","title":"Pseudo-triplet Guided Few-shot Composed Image Retrieval","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2410.14101","title":"Multi-Source Spatial Knowledge Understanding for Immersive Visual Text-to-Speech","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2412.03297","title":"Composed Image Retrieval for Training-Free Domain Conversion","created":"2024-12-04","cited_by_count":4,"area":null},{"id":"2412.11409","title":"Multi-modal and Multi-scale Spatial Environment Understanding for Immersive Visual Text-to-Speech","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2505.17796","title":"DetailFusion: A Dual-branch Framework with Detail Enhancement for Composed Image Retrieval","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2509.14746","title":"Chain-of-Thought Re-ranking for Image Retrieval Tasks","created":"2025-09-18","cited_by_count":4,"area":"lr"},{"id":"2603.16737","title":"Retrieving Counterfactuals Improves Visual In-Context Learning","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2410.17393","title":"Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image Retrieval","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2502.07215","title":"PDV: Prompt Directional Vectors for Zero-shot Composed Image Retrieval","created":"2025-02-11","cited_by_count":3,"area":null},{"id":"2503.19145","title":"Compositional Caching for Training-free Open-vocabulary Attribute Detection","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2602.23029","title":"WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2406.09188","title":"An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2410.23736","title":"Modality and Task Adaptation for Enhanced Zero-shot Composed Image Retrieval","created":"2024-10-31","cited_by_count":2,"area":"moe"},{"id":"2501.08347","title":"SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval","created":"2025-01-12","cited_by_count":2,"area":null},{"id":"2503.01334","title":"Composed Multi-modal Retrieval: A Survey of Approaches and Applications","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2503.05204","title":"Data-Efficient Generalization for Zero-shot Composed Image Retrieval","created":"2025-03-07","cited_by_count":2,"area":"mllm"},{"id":"2504.17990","title":"From Mapping to Composing: A Two-Stage Framework for Zero-shot Composed Image Retrieval","created":"2025-04-25","cited_by_count":2,"area":null},{"id":"2507.05970","title":"Automatic Synthesis of High-Quality Triplet Data for Composed Image Retrieval","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2507.12819","title":"MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval","created":"2025-07-17","cited_by_count":2,"area":"lr"},{"id":"2509.23242","title":"TATTOO: Training-free AesTheTic-aware Outfit recOmmendation","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2601.11393","title":"Heterogeneous Uncertainty-Guided Composed Image Retrieval with Fine-Grained Probabilistic Learning","created":"2026-01-16","cited_by_count":2,"area":null},{"id":"2603.01493","title":"PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2604.14710","title":"G-MIXER: Geodesic Mixup-based Implicit Semantic Expansion and Explicit Semantic Re-ranking for Zero-Shot Composed Image Retrieval","created":"2026-04-16","cited_by_count":2,"area":null},{"id":"2604.20318","title":"UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval","created":"2026-04-22","cited_by_count":2,"area":"mllm"},{"id":"2605.21261","title":"STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2607.02284","title":"FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval","created":"2026-07-02","cited_by_count":2,"area":"diffusion"},{"id":"2404.19360","title":"Large Language Model Informed Patent Image Retrieval","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2409.08381","title":"Rethinking Prompting Strategies for Multi-Label Recognition with Partial Annotations","created":"2024-09-12","cited_by_count":1,"area":"mllm"},{"id":"2410.01536","title":"EUFCC-CIR: a Composed Image Retrieval Dataset for GLAM Collections","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2507.07135","title":"FACap: A Large-scale Fashion Dataset for Fine-grained Composed Image Retrieval","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.26012","title":"SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2509.26330","title":"SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval","created":"2025-09-30","cited_by_count":1,"area":"mllm"},{"id":"2601.14060","title":"Fine-Grained Zero-Shot Composed Image Retrieval with Complementary Visual-Semantic Integration","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2601.16125","title":"Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2601.16582","title":"X-Aligner: Composed Visual Retrieval without the Bells and Whistles","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2601.20511","title":"Say Cheese! Detail-Preserving Portrait Collection Generation via Natural Language Edits","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2602.00813","title":"Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval","created":"2026-01-31","cited_by_count":1,"area":"mllm"},{"id":"2602.08603","title":"OSCAR: Optimization-Steered Agentic Planning for Composed Image Retrieval","created":"2026-02-09","cited_by_count":1,"area":"agents"},{"id":"2602.19615","title":"Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness","created":"2026-02-23","cited_by_count":1,"area":"lr"},{"id":"2604.11539","title":"CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2606.07032","title":"Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2607.02425","title":"Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2607.27959","title":"FiRE: Enhancing MLLMs with Fine-Grained Context Learning for Complex Image Retrieval","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2608.05149","title":"CoCo-IR: Contextual Composed Image Retrieval","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.22500","title":"Learning Sample-wise Rank-aware Interpolation Weights for Composed Visual Data Retrieval","created":"2026-08-23","cited_by_count":1,"area":null},{"id":"2508.11272","title":"Enhancing Supervised Composed Image Retrieval via Reasoning-Augmented Representation Engineering","created":"2025-08-15","cited_by_count":0,"area":"lr"},{"id":"2510.05411","title":"Personalizing Retrieval using Joint Embeddings or \"the Return of Fluffy\"","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2511.22253","title":"UNION: A Lightweight Target Representation for Efficient Zero-Shot Image-Guided Retrieval with Optional Textual Queries","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2512.01636","title":"Generative Editing in the Joint Vision-Language Space for Zero-Shot Composed Image Retrieval","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2602.22510","title":"Pix2Key: Controllable Open-Vocabulary Retrieval with Semantic Decomposition and Self-Supervised Visual Dictionary Learning","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.04037","title":"DQE-CIR: Distinctive Query Embeddings through Learnable Attribute Weights and Target Relative Negative Sampling in Composed Image Retrieval","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.05393","title":"Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.12904","title":"A Sanity Check on Composed Image Retrieval","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.02892","title":"AlbumFill: Album-Guided Reasoning and Retrieval for Personalized Image Completion","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.08389","title":"Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.14787","title":"Do Composed Image Retrieval Benchmarks Require Multimodal Composition?","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.24442","title":"Benchmarking Composed Image Retrieval for Applied Earth Observation","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2605.26734","title":"CIRCLED: A Multi-turn CIR Dataset with Consistent Dialogues across Domains","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.12294","title":"Bridging the Modality Gap in Forensic Image Retrieval","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.31222","title":"Thinking Before Retrieving: Robust Zero-Shot Composed Image Retrieval via Strategic Planning and Self-Criticism","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.12621","title":"Towards Vision-Free CIR: Attribute-Augmented Scoring and LLM-Based Reranking for Zero-Shot Composed Image Retrieval","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.19115","title":"CR-Refiner: An Object-Centric Optimal Transport Reranker for Edit-Conditioned 3D Scene Retrieval","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.23102","title":"Training-Free Pseudo-Fusion for Composed Image Retrieval with Diffusion Models and Multimodal Large Language Models","created":"2026-08-24","cited_by_count":0,"area":"mllm"},{"id":"2608.25305","title":"MulVec: Fine-Grained Role-Aware Matching for Training-Free Zero-Shot Composed Image Retrieval","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":"100"}