{"total":58,"rows":[{"id":"2506.17267","title":"CF-VLM:CounterFactual Vision-Language Fine-tuning","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"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":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"id":"2506.03448","title":"RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions","created":"2025-06-03","cited_by_count":10,"area":null},{"id":"2508.11317","title":"Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models","created":"2025-08-15","cited_by_count":7,"area":"mllm"},{"id":"2509.15772","title":"Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation","created":"2025-09-19","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":"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":"2511.20515","title":"HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning","created":"2025-11-25","cited_by_count":5,"area":"mllm"},{"id":"2507.07985","title":"Common Data Properties Limit Object-Attribute Binding in CLIP","created":"2025-07-10","cited_by_count":4,"area":"mllm"},{"id":"2412.15396","title":"Learning Visual Composition through Improved Semantic Guidance","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2507.06210","title":"CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions","created":"2025-07-08","cited_by_count":3,"area":"mllm"},{"id":"2602.05729","title":"Adaptive Global and Fine-Grained Perceptual Fusion for MLLM Embeddings Compatible with Hard Negative Amplification","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2505.20152","title":"MMGeoLM: Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models","created":"2025-05-26","cited_by_count":2,"area":"mllm"},{"id":"2509.03897","title":"SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation","created":"2025-09-04","cited_by_count":2,"area":null},{"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":"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":"2603.09185","title":"DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval","created":"2026-03-10","cited_by_count":2,"area":"rag"},{"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":"2503.18507","title":"Can Text-to-Video Generation help Video-Language Alignment?","created":"2025-03-24","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":"2506.09691","title":"Adding simple structure at inference improves Vision-Language Compositionality","created":"2025-06-11","cited_by_count":1,"area":"mllm"},{"id":"2507.03434","title":"Unlearning the Noisy Correspondence Makes CLIP More Robust","created":"2025-07-04","cited_by_count":1,"area":"mllm"},{"id":"2509.01959","title":"Structure-aware Contrastive Learning for Diagram Understanding of Multimodal Models","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2510.13315","title":"Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models","created":"2025-10-15","cited_by_count":1,"area":"mllm"},{"id":"2511.14271","title":"Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation","created":"2025-11-18","cited_by_count":1,"area":"mllm"},{"id":"2511.23170","title":"PowerCLIP: Powerset Alignment for Contrastive Pre-Training","created":"2025-11-28","cited_by_count":1,"area":"mllm"},{"id":"2602.01370","title":"PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator Ensembles","created":"2026-02-01","cited_by_count":1,"area":"mllm"},{"id":"2603.29258","title":"Omni-NegCLIP: Enhancing CLIP with Front-Layer Contrastive Fine-Tuning for Comprehensive Negation Understanding","created":"2026-03-31","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":"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":"2412.15632","title":"A New Method to Capturing Compositional Knowledge in Linguistic Space","created":"2024-12-20","cited_by_count":0,"area":"mllm"},{"id":"2503.13021","title":"Dynamic Relation Inference via Verb Embeddings","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2505.05635","title":"Neural Catalog: Scaling Species Recognition with Catalog of Life-Augmented Generation","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2509.19207","title":"Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs","created":"2025-09-23","cited_by_count":0,"area":"mllm"},{"id":"2509.23770","title":"GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2510.03955","title":"Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2511.16527","title":"Contrastive vision-language learning with paraphrasing and negation","created":"2025-11-20","cited_by_count":0,"area":"mllm"},{"id":"2511.20274","title":"SCLARO: A Dataset for Grounded Scenario-Level Scene Understanding and ScenarioCLIP for Benchmarking","created":"2025-11-25","cited_by_count":0,"area":null},{"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":"2602.23589","title":"Pseudo Contrastive Learning for Diagram Comprehension in Multimodal Models","created":"2026-02-27","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":"2603.02557","title":"CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignment","created":"2026-03-03","cited_by_count":0,"area":"mllm"},{"id":"2603.06873","title":"PICS: Pairwise Image Compositing with Spatial Interactions","created":"2026-03-06","cited_by_count":0,"area":"diffusion"},{"id":"2603.15253","title":"HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning","created":"2026-03-16","cited_by_count":0,"area":"mllm"},{"id":"2603.24804","title":"GoldiCLIP: The Goldilocks Approach for Balancing Explicit Supervision for Language-Image Pretraining","created":"2026-03-25","cited_by_count":0,"area":"mllm"},{"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":"2604.13313","title":"Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"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":"2605.22651","title":"What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2607.09263","title":"Semantic Hardness Is Not Visual Hardness: Sign-Aware Hard Negative Mining for Sign Language Retrieval","created":"2026-07-10","cited_by_count":0,"area":null},{"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":"2608.29604","title":"RePair: Turning Retrieval Failures into Counterfactual Hard Pairs","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.07937","title":"TDDN: Text-aligned Diffused DINO Network for Puzzle Understanding","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2610.16977","title":"The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors","created":"2026-10-12","cited_by_count":0,"area":"mllm"}],"next_cursor":null}