{"total":103,"rows":[{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103,"area":null},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"area":null},{"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":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2510.13515","title":"UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning","created":"2025-10-15","cited_by_count":42,"area":null},{"id":"2502.03566","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","created":"2025-02-05","cited_by_count":31,"area":null},{"id":"2501.10913","title":"Know \"No\" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP","created":"2025-01-19","cited_by_count":28,"area":null},{"id":"2506.09284","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","created":"2025-06-10","cited_by_count":23,"area":null},{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","cited_by_count":21,"area":null},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20,"area":null},{"id":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2410.05210","title":"Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality","created":"2024-10-07","cited_by_count":17,"area":null},{"id":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"area":null},{"id":"2502.19842","title":"CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation","created":"2025-02-27","cited_by_count":14,"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":"2312.02338","title":"A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2407.15408","title":"Chronologically Accurate Retrieval for Temporal Grounding of Motion-Language Models","created":"2024-07-22","cited_by_count":12,"area":null},{"id":"2411.11927","title":"FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2401.00094","title":"Generating Enhanced Negatives for Training Language-Based Object Detectors","created":"2023-12-29","cited_by_count":11,"area":null},{"id":"2312.12661","title":"Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining","created":"2023-12-19","cited_by_count":10,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2505.22079","title":"Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2507.14902","title":"U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs","created":"2025-07-20","cited_by_count":10,"area":null},{"id":"2410.00905","title":"Removing Distributional Discrepancies in Captions Improves Image-Text Alignment","created":"2024-10-01","cited_by_count":8,"area":null},{"id":"2511.19278","title":"ReMatch: Boosting Representation through Matching for Multimodal Retrieval","created":"2025-11-24","cited_by_count":8,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2407.17960","title":"The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communication","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2502.20104","title":"New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2503.17080","title":"Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2406.09952","title":"BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2409.03025","title":"No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2506.08227","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2402.08919","title":"Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2404.15721","title":"SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision","created":"2024-04-24","cited_by_count":4,"area":null},{"id":"2410.10291","title":"Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2412.08859","title":"ViUniT: Visual Unit Tests for More Robust Visual Programming","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2504.08368","title":"FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2504.08907","title":"Spatial Audio Processing with Large Language Model on Wearable Devices","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2504.20902","title":"Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers","created":"2025-04-29","cited_by_count":4,"area":null},{"id":"2506.04209","title":"Language-Image Alignment with Fixed Text Encoders","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2509.25339","title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2407.05118","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","created":"2024-07-06","cited_by_count":3,"area":null},{"id":"2407.15296","title":"Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection","created":"2024-07-21","cited_by_count":3,"area":null},{"id":"2412.15396","title":"Learning Visual Composition through Improved Semantic Guidance","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2506.03096","title":"FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2508.15418","title":"LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2602.22278","title":"RETLLM: Training and Data-Free MLLMs for Multimodal Information Retrieval","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2602.23543","title":"Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","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":"2410.11963","title":"CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2507.01201","title":"Escaping Plato's Cave: JAM for Aligning Independently Trained Vision and Language Models","created":"2025-07-01","cited_by_count":2,"area":null},{"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":"2512.17178","title":"ABE-CLIP: Training-Free Attribute Binding Enhancement for Compositional Image-Text Matching","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2602.03282","title":"Global Geometry Is Not Enough for Vision Representations","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2606.01414","title":"Agent Skills Should Go Beyond Text: The Case for Visual Skills","created":"2026-05-31","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":"2412.07161","title":"Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2502.09645","title":"From No to Know: Taxonomy, Challenges, and Opportunities for Negation Understanding in Multimodal Foundation Models","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2504.21850","title":"Visual Compositional Tuning","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2505.22943","title":"Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2510.18795","title":"ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2601.22570","title":"Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2606.03715","title":"Text-to-Image Models Need Less from Text Encoders Than You Think","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2607.12290","title":"The Sound of Absence: Audio-Language Embedding Models Struggle with Negation","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2608.03631","title":"SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classification","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.15601","title":"Quantum Models with Multi-Stage Training for Compositional Concept Generalization","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2410.12874","title":"On Debiasing Text Embeddings Through Context Injection","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2505.08283","title":"DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalities","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2508.09852","title":"Perceptual Reality Transformer: What Must an Illustration Preserve?","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2602.07532","title":"Evaluating Object-Centric Models beyond Object Discovery","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2602.16545","title":"Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2602.16689","title":"Are Object-Centric Representations Better At Compositional Generalization?","created":"2026-02-18","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":"2603.25722","title":"No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.16351","title":"Training for Compositional Sensitivity Reduces Dense Retrieval Generalization","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.16487","title":"Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.06080","title":"MSD-Score: Multi-Scale Distributional Scoring for Reference-Free Image Caption Evaluation","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.17727","title":"GraSP-VL: Length as a Semantic Granularity Interface for Vision-Language Representations","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.31503","title":"How can embedding models bind concepts?","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.03871","title":"Visual Instruction Tuning Aligns Modalities through Abstraction","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.00428","title":"HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.03143","title":"Text as Partial Constraint: Core-Residual Alignment for Robust Vision-Language Learning","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.27857","title":"EEG-EditBench: Probing Visual Information in EEG-Image Retrieval Models with Controlled Image Edits","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.12426","title":"Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.15971","title":"The Limits of Binding in Dual Encoders","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.18521","title":"Which Negatives Matter? Ask Your Text Encoder: Adaptive Similarity Margins for Dense-Caption Retrieval","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.29604","title":"RePair: Turning Retrieval Failures into Counterfactual Hard Pairs","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.00816","title":"Can Scene Text Recognition Read Rare Compositions?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.04801","title":"Whose record is this? Diagnosing and authorizing record use in personalized multimodal models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.23717","title":"BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.30540","title":"Don't CLAP: Are Music-Text Models Bag-of-Words?","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32462","title":"Can Motion-Language Models Ground Structure? STRIDE for Evaluating the Evaluators","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33319","title":"PhysAlign: A Benchmark for Evidence-Grounded Role Alignment in Multimodal Physics Reasoning","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.37230","title":"Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":"100"}