{"total":33,"rows":[{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218,"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":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114,"area":"mllm"},{"id":"2207.11514","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","created":"2022-07-23","cited_by_count":95,"area":"mllm"},{"id":"2503.06287","title":"Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding","created":"2025-03-08","cited_by_count":83,"area":"mllm"},{"id":"2210.09996","title":"Perceptual Grouping in Contrastive Vision-Language Models","created":"2022-10-18","cited_by_count":82,"area":"mllm"},{"id":"2306.04356","title":"Fine-Grained Visual Prompting","created":"2023-06-07","cited_by_count":82,"area":"mllm"},{"id":"2306.12424","title":"VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution","created":"2023-06-21","cited_by_count":52,"area":"mllm"},{"id":"2403.12488","title":"DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM","created":"2024-03-19","cited_by_count":46,"area":"mllm"},{"id":"2410.12332","title":"MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs","created":"2024-10-16","cited_by_count":39,"area":"mllm"},{"id":"2503.10437","title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models","created":"2025-03-13","cited_by_count":35,"area":"mllm"},{"id":"2305.14014","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2312.15043","title":"GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection","created":"2023-12-22","cited_by_count":20,"area":"mllm"},{"id":"2406.18722","title":"Towards Open-World Grasping with Large Vision-Language Models","created":"2024-06-26","cited_by_count":15,"area":"mllm"},{"id":"2503.09837","title":"On the Limitations of Vision-Language Models in Understanding Image Transforms","created":"2025-03-12","cited_by_count":13,"area":"mllm"},{"id":"2502.08779","title":"BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models","created":"2025-02-12","cited_by_count":11,"area":"mllm"},{"id":"2509.15178","title":"Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding","created":"2025-09-18","cited_by_count":9,"area":"mllm"},{"id":"2505.17440","title":"VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models","created":"2025-05-23","cited_by_count":8,"area":"mllm"},{"id":"2404.19128","title":"Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM","created":"2024-04-29","cited_by_count":3,"area":"mllm"},{"id":"2606.07953","title":"Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines","created":"2026-06-06","cited_by_count":3,"area":"mllm"},{"id":"2606.07965","title":"Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline","created":"2026-06-06","cited_by_count":3,"area":"mllm"},{"id":"2407.20034","title":"MaskInversion: Localized Embeddings via Optimization of Explainability Maps","created":"2024-07-29","cited_by_count":2,"area":"mllm"},{"id":"2412.18675","title":"TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models","created":"2024-12-24","cited_by_count":2,"area":"mllm"},{"id":"2510.00523","title":"VIRTUE: Visual-Interactive Text-Image Universal Embedder","created":"2025-10-01","cited_by_count":2,"area":"mllm"},{"id":"2606.31054","title":"ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs","created":"2026-06-30","cited_by_count":2,"area":"mllm"},{"id":"2305.11497","title":"TreePrompt: Learning to Compose Tree Prompts for Explainable Visual Grounding","created":"2023-05-19","cited_by_count":1,"area":"mllm"},{"id":"2405.10610","title":"Harnessing Vision-Language Pretrained Models with Temporal-Aware Adaptation for Referring Video Object Segmentation","created":"2024-05-17","cited_by_count":1,"area":"mllm"},{"id":"2505.02278","title":"Compositional Image-Text Matching and Retrieval by Grounding Entities","created":"2025-05-04","cited_by_count":1,"area":"mllm"},{"id":"2412.08110","title":"The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding","created":"2024-12-11","cited_by_count":0,"area":"mllm"},{"id":"2603.08930","title":"Using Vision Language Foundation Models to Generate Plant Simulation Configurations via In-Context Learning","created":"2026-03-09","cited_by_count":0,"area":"mllm"},{"id":"2604.11197","title":"MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration","created":"2026-04-13","cited_by_count":0,"area":"mllm"},{"id":"2606.01710","title":"Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs","created":"2026-06-01","cited_by_count":0,"area":"mllm"},{"id":"2608.15061","title":"Do Visual Grounding Decoders Need Feed-Forward Networks? A Controlled Study over Frozen Vision-Language Features","created":"2026-08-15","cited_by_count":0,"area":"mllm"}],"next_cursor":null}