{"total":52,"rows":[{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474,"area":null},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178,"area":"mllm"},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135,"area":null},{"id":"2408.08632","title":"A Survey on Benchmarks of Multimodal Large Language Models","created":"2024-08-16","cited_by_count":82,"area":"mllm"},{"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":"2306.01879","title":"Revisiting the Role of Language Priors in Vision-Language Models","created":"2023-06-02","cited_by_count":50,"area":"mllm"},{"id":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"id":"2408.15769","title":"A Survey on Evaluation of Multimodal Large Language Models","created":"2024-08-28","cited_by_count":46,"area":"lr"},{"id":"2407.03471","title":"Learning Action and Reasoning-Centric Image Editing from Videos and Simulations","created":"2024-07-03","cited_by_count":32,"area":null},{"id":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31,"area":null},{"id":"2405.01926","title":"Auto-Encoding Morph-Tokens for Multimodal LLM","created":"2024-05-03","cited_by_count":30,"area":"mllm"},{"id":"2506.09987","title":"A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs","created":"2025-06-11","cited_by_count":30,"area":"lr"},{"id":"2311.15206","title":"Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding","created":"2023-11-26","cited_by_count":29,"area":null},{"id":"2409.18142","title":"A Survey on Multimodal Benchmarks: In the Era of Large AI Models","created":"2024-09-21","cited_by_count":27,"area":"mllm"},{"id":"2311.07022","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23,"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":"2406.05191","title":"DiffusionPID: Interpreting Diffusion via Partial Information Decomposition","created":"2024-06-07","cited_by_count":16,"area":"diffusion"},{"id":"2406.05814","title":"TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models","created":"2024-06-09","cited_by_count":12,"area":"mllm"},{"id":"2410.16719","title":"Progressive Compositionality in Text-to-Image Generative Models","created":"2024-10-22","cited_by_count":12,"area":"diffusion"},{"id":"2405.19722","title":"QClusformer: A Quantum Transformer-based Framework for Unsupervised Visual Clustering","created":"2024-05-30","cited_by_count":11,"area":null},{"id":"2411.05195","title":"Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder","created":"2024-11-07","cited_by_count":11,"area":"lr"},{"id":"2504.03970","title":"VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models","created":"2025-04-04","cited_by_count":11,"area":"mllm"},{"id":"2405.19725","title":"Quantum Visual Feature Encoding Revisited","created":"2024-05-30","cited_by_count":10,"area":null},{"id":"2404.09387","title":"RankCLIP: Ranking-Consistent Language-Image Pretraining","created":"2024-04-15","cited_by_count":9,"area":"mllm"},{"id":"2310.03734","title":"Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency","created":"2023-10-05","cited_by_count":8,"area":null},{"id":"2406.09240","title":"Comparison Visual Instruction Tuning","created":"2024-06-13","cited_by_count":8,"area":"lr"},{"id":"2410.22315","title":"Natural Language Inference Improves Compositionality in Vision-Language Models","created":"2024-10-29","cited_by_count":8,"area":"lr"},{"id":"2405.17201","title":"Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View","created":"2024-05-27","cited_by_count":7,"area":"lr"},{"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":"2603.22228","title":"SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation","created":"2026-03-23","cited_by_count":6,"area":"alignment"},{"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":"2508.02329","title":"VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions","created":"2025-08-04","cited_by_count":5,"area":"mllm"},{"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":"2312.00236","title":"Brainformer: Mimic Human Visual Brain Functions to Machine Vision Models via fMRI","created":"2023-11-30","cited_by_count":3,"area":null},{"id":"2505.00759","title":"Multimodal Language Models as Text-to-Image Model Evaluators","created":"2025-05-01","cited_by_count":3,"area":"mllm"},{"id":"2406.01432","title":"ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models","created":"2024-06-03","cited_by_count":2,"area":"mllm"},{"id":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","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":"2510.16540","title":"Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions","created":"2025-10-18","cited_by_count":2,"area":"lr"},{"id":"2604.00799","title":"Multimodal Language Models Cannot Spot Spatial Inconsistencies","created":"2026-04-01","cited_by_count":2,"area":"mllm"},{"id":"2506.07196","title":"SAP-Bench: Benchmarking Multimodal Large Language Models in Surgical Action Planning","created":"2025-06-08","cited_by_count":1,"area":"mllm"},{"id":"2506.09691","title":"Adding simple structure at inference improves Vision-Language Compositionality","created":"2025-06-11","cited_by_count":1,"area":"mllm"},{"id":"2604.08324","title":"Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2509.24192","title":"Talk in Pieces, See in Whole: Disentangled and Hierarchical Representation Learning in Language-based Object Detection","created":"2025-09-29","cited_by_count":0,"area":"mllm"},{"id":"2603.11689","title":"Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"id":"2606.07645","title":"FineGen: A VLM-based Multi-Agent Framework for Fine-Grained Image-Text Dataset Construction","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2608.25575","title":"MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations","created":"2026-08-26","cited_by_count":0,"area":"mllm"},{"id":"2609.31965","title":"SNIP++: Fine-Grained Symbolic-Numerical Alignment for Symbolic Regression","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.38285","title":"GaugeVLM: Structuring Spatial Supervision with Measured Geometric Interventions","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2610.16441","title":"VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}