{"total":22,"rows":[{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111,"area":"mllm"},{"id":"2406.10100","title":"SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding","created":"2024-06-14","cited_by_count":104,"area":"mllm"},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2404.00906","title":"From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models","created":"2024-04-01","cited_by_count":43,"area":"mllm"},{"id":"2205.11169","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","created":"2022-05-23","cited_by_count":30,"area":"mllm"},{"id":"2408.09429","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","created":"2024-08-18","cited_by_count":30,"area":"mllm"},{"id":"2305.12476","title":"Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models","created":"2023-05-21","cited_by_count":27,"area":"mllm"},{"id":"2302.00268","title":"Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection","created":"2023-02-01","cited_by_count":22,"area":"mllm"},{"id":"2410.15364","title":"Scene Graph Generation with Role-Playing Large Language Models","created":"2024-10-20","cited_by_count":16,"area":"mllm"},{"id":"2406.09121","title":"MMRel: Benchmarking Relation Understanding in Multi-Modal Large Language Models","created":"2024-06-13","cited_by_count":10,"area":"mllm"},{"id":"2404.15785","title":"Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer","created":"2024-04-24","cited_by_count":7,"area":"mllm"},{"id":"2506.08189","title":"Open World Scene Graph Generation using Vision Language Models","created":"2025-06-09","cited_by_count":7,"area":"mllm"},{"id":"2307.04838","title":"CREPE: Learnable Prompting With CLIP Improves Visual Relationship Prediction","created":"2023-07-10","cited_by_count":4,"area":"mllm"},{"id":"2505.19474","title":"Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models","created":"2025-05-26","cited_by_count":4,"area":"mllm"},{"id":"2509.21576","title":"Vision Language Models Cannot Plan, but Can They Formalize?","created":"2025-09-25","cited_by_count":3,"area":"mllm"},{"id":"2510.22102","title":"Mitigating Coordinate Prediction Bias from Positional Encoding Failures","created":"2025-10-25","cited_by_count":2,"area":"mllm"},{"id":"2403.16184","title":"Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement","created":"2024-03-24","cited_by_count":1,"area":"mllm"},{"id":"2506.15583","title":"DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement","created":"2025-06-18","cited_by_count":1,"area":"mllm"},{"id":"2510.21069","title":"ZING-3D: Zero-shot Incremental 3D Scene Graphs via Vision-Language Models","created":"2025-10-24","cited_by_count":1,"area":"mllm"},{"id":"2603.07659","title":"Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework","created":"2026-03-08","cited_by_count":1,"area":"mllm"},{"id":"2402.19116","title":"How to Understand \"Support\"? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding","created":"2024-02-29","cited_by_count":0,"area":"mllm"},{"id":"2503.15846","title":"A Closer Look at Dynamic Scene Graph Generation In the Era of Multimodal Large Language Models","created":"2025-03-20","cited_by_count":0,"area":"mllm"}],"next_cursor":null}