{"total":53,"rows":[{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75,"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":"2411.02537","title":"INQUIRE: A Natural World Text-to-Image Retrieval Benchmark","created":"2024-11-04","cited_by_count":33,"area":"mllm"},{"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":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2504.01916","title":"FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs","created":"2025-04-02","cited_by_count":23,"area":"mllm"},{"id":"2406.08164","title":"ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs","created":"2024-06-12","cited_by_count":21,"area":"lr"},{"id":"2502.09411","title":"ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation","created":"2025-02-13","cited_by_count":21,"area":"diffusion"},{"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":"2512.10941","title":"Mull-Tokens: Modality-Agnostic Latent Thinking","created":"2025-12-11","cited_by_count":19,"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":"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":"2404.14715","title":"FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction","created":"2024-04-23","cited_by_count":17,"area":"mllm"},{"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":"2604.21806","title":"TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval","created":"2026-04-23","cited_by_count":15,"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":"2402.15021","title":"CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models","created":"2024-02-22","cited_by_count":12,"area":"mllm"},{"id":"2406.10889","title":"VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment","created":"2024-06-16","cited_by_count":10,"area":"lr"},{"id":"2406.09240","title":"Comparison Visual Instruction Tuning","created":"2024-06-13","cited_by_count":8,"area":"lr"},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2404.08535","title":"Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking","created":"2024-04-12","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":"2505.17955","title":"Diffusion Classifiers Understand Compositionality, but Conditions Apply","created":"2025-05-23","cited_by_count":7,"area":"diffusion"},{"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":"2503.04556","title":"Compositional Causal Reasoning Evaluation in Language Models","created":"2025-03-06","cited_by_count":6,"area":"lr"},{"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":"2508.20783","title":"Evaluating Compositional Generalisation in VLMs and Diffusion Models","created":"2025-08-28","cited_by_count":5,"area":"diffusion"},{"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":"2504.10995","title":"TMCIR: Token Merge Benefits Composed Image Retrieval","created":"2025-04-15","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":"2412.08111","title":"Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models","created":"2024-12-11","cited_by_count":3,"area":"mllm"},{"id":"2510.05586","title":"CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval","created":"2025-10-07","cited_by_count":3,"area":"mllm"},{"id":"2603.02098","title":"Efficient and High-Fidelity Omni Modality Retrieval","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2404.18316","title":"Position: Do Not Explain Vision Models Without Context","created":"2024-04-28","cited_by_count":2,"area":null},{"id":"2411.15605","title":"GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2504.04740","title":"SCRAMBLe : Enhancing Multimodal LLM Compositionality with Synthetic Preference Data","created":"2025-04-07","cited_by_count":2,"area":"mllm"},{"id":"2511.06653","title":"HiMo-CLIP: Modeling Semantic Hierarchy and Monotonicity in Vision-Language Alignment","created":"2025-11-10","cited_by_count":2,"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":"2502.00711","title":"VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework","created":"2025-02-02","cited_by_count":1,"area":"lr"},{"id":"2512.04847","title":"Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2603.25891","title":"Few Shots Text to Image Retrieval: New Benchmarking Dataset and Optimization Methods","created":"2026-03-26","cited_by_count":1,"area":"mllm"},{"id":"2604.11496","title":"Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2408.05894","title":"GlyphPattern: An Abstract Pattern Recognition Benchmark for Vision-Language Models","created":"2024-08-12","cited_by_count":0,"area":"mllm"},{"id":"2409.01389","title":"CV-Probes: Studying the interplay of lexical and world knowledge in visually grounded verb understanding","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2507.00537","title":"Not All Attention Heads Are What You Need: Refining CLIP's Image Representation with Attention Ablation","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2511.08075","title":"CLIP is All You Need for Human-like Semantic Representations in Stable Diffusion","created":"2025-11-11","cited_by_count":0,"area":"diffusion"},{"id":"2601.12809","title":"Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data","created":"2026-01-19","cited_by_count":0,"area":"mllm"},{"id":"2604.21935","title":"Math Takes Two: A test for emergent mathematical reasoning in communication","created":"2026-03-30","cited_by_count":0,"area":"lr"},{"id":"2607.27779","title":"CXR-Retrieve: Compositional Text-to-Image Retrieval in Chest Radiography","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.00994","title":"Entity-Faithful Repair of Synthetic Supervision for Zero-Shot Image Captioning","created":"2026-08-02","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":"2609.37230","title":"Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}