{"total":55,"rows":[{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610,"area":"mllm"},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2408.08632","title":"A Survey on Benchmarks of Multimodal Large Language Models","created":"2024-08-16","cited_by_count":82,"area":"mllm"},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"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":"2306.08832","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","created":"2023-06-15","cited_by_count":41,"area":"mllm"},{"id":"2403.18346","title":"Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective","created":"2024-03-27","cited_by_count":39,"area":"mllm"},{"id":"2505.17127","title":"Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts","created":"2025-05-21","cited_by_count":32,"area":"mllm"},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23,"area":"mllm"},{"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":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"id":"2304.03659","title":"Probing Conceptual Understanding of Large Visual-Language Models","created":"2023-04-07","cited_by_count":17,"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":"2401.17981","title":"From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information","created":"2024-01-31","cited_by_count":16,"area":"mllm"},{"id":"2403.16442","title":"If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions","created":"2024-03-25","cited_by_count":14,"area":"mllm"},{"id":"2402.15021","title":"CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models","created":"2024-02-22","cited_by_count":12,"area":"mllm"},{"id":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"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":"2308.03151","title":"Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models","created":"2023-08-06","cited_by_count":10,"area":"mllm"},{"id":"2310.08577","title":"Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models","created":"2023-10-12","cited_by_count":9,"area":"mllm"},{"id":"2407.01081","title":"CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation","created":"2024-07-01","cited_by_count":8,"area":"mllm"},{"id":"2503.17827","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","created":"2025-03-22","cited_by_count":8,"area":"mllm"},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2505.18434","title":"TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP","created":"2025-05-24","cited_by_count":7,"area":"mllm"},{"id":"2209.06103","title":"VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models","created":"2022-09-12","cited_by_count":6,"area":"mllm"},{"id":"2308.10509","title":"An Examination of the Compositionality of Large Generative Vision-Language Models","created":"2023-08-21","cited_by_count":6,"area":"mllm"},{"id":"2308.16689","title":"ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation","created":"2023-08-31","cited_by_count":6,"area":"mllm"},{"id":"2310.02777","title":"The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-Language Models","created":"2023-10-04","cited_by_count":6,"area":"mllm"},{"id":"2505.24424","title":"Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning","created":"2025-05-30","cited_by_count":5,"area":"mllm"},{"id":"2601.03500","title":"SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models","created":"2026-01-07","cited_by_count":3,"area":"mllm"},{"id":"2305.18786","title":"Scalable Performance Analysis for Vision-Language Models","created":"2023-05-30","cited_by_count":2,"area":"mllm"},{"id":"2407.17914","title":"Vision-Language Models Align with Human Neural Representations in Concept Processing","created":"2024-07-25","cited_by_count":2,"area":"mllm"},{"id":"2412.04429","title":"Grounding Descriptions in Images informs Zero-Shot Visual Recognition","created":"2024-12-05","cited_by_count":1,"area":"mllm"},{"id":"2501.11469","title":"MASS: Overcoming Language Bias in Image-Text Matching","created":"2025-01-20","cited_by_count":1,"area":"mllm"},{"id":"2507.09615","title":"Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score","created":"2025-07-13","cited_by_count":1,"area":"mllm"},{"id":"2606.13288","title":"Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality","created":"2026-06-11","cited_by_count":1,"area":"mllm"},{"id":"2607.23271","title":"What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features","created":"2026-07-25","cited_by_count":1,"area":"mllm"},{"id":"2608.00147","title":"RadPRISM: Schema-stratified radiology-report supervision for concept-disentangled image representations and visual grounding","created":"2026-07-31","cited_by_count":1,"area":"mllm"},{"id":"2302.01582","title":"Controlling for Stereotypes in Multimodal Language Model Evaluation","created":"2023-02-03","cited_by_count":0,"area":"mllm"},{"id":"2510.23253","title":"A Video Is Not Worth a Thousand Words","created":"2025-10-27","cited_by_count":0,"area":"mllm"},{"id":"2512.17121","title":"The Effect of Negation on CLIP in Medical Imaging: Limitations of Contrastive Language-Image Pretraining","created":"2025-12-18","cited_by_count":0,"area":"mllm"},{"id":"2601.04824","title":"SOVABench: A Vehicle Surveillance Action Retrieval Benchmark for Multimodal Large Language Models","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"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":"2602.02043","title":"Auto-Comp: An Automated Pipeline for Scalable Compositional Probing of Contrastive Vision-Language Models","created":"2026-02-02","cited_by_count":0,"area":"mllm"},{"id":"2602.21854","title":"FewMMBench: A Benchmark for Multimodal Few-Shot Learning","created":"2026-02-25","cited_by_count":0,"area":"mllm"},{"id":"2604.13313","title":"Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2604.17217","title":"Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual Reliability","created":"2026-04-19","cited_by_count":0,"area":"mllm"},{"id":"2604.22822","title":"DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models","created":"2026-04-18","cited_by_count":0,"area":"mllm"},{"id":"2605.21728","title":"BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model","created":"2026-05-20","cited_by_count":0,"area":"mllm"},{"id":"2608.03691","title":"Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"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":"2609.05149","title":"From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making","created":"2026-09-04","cited_by_count":0,"area":"mllm"},{"id":"2609.20139","title":"Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models","created":"2026-09-17","cited_by_count":0,"area":"mllm"},{"id":"2610.17440","title":"Know-Thy-Not: Training-Free Targeted Negation in Dual-Encoder Vision-Language Models","created":"2026-10-12","cited_by_count":0,"area":"mllm"}],"next_cursor":null}