{"total":120,"rows":[{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603,"area":"lr"},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375,"area":"diffusion"},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304,"area":null},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293,"area":"lr"},{"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":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177,"area":null},{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151,"area":null},{"id":"2303.15233","title":"Text-to-Image Diffusion Models are Zero-Shot Classifiers","created":"2023-03-27","cited_by_count":143,"area":"diffusion"},{"id":"2211.09646","title":"Language Conditioned Spatial Relation Reasoning for 3D Object Grounding","created":"2022-11-17","cited_by_count":122,"area":null},{"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":"2306.01293","title":"LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning","created":"2023-06-02","cited_by_count":107,"area":null},{"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":"2505.14231","title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning","created":"2025-05-20","cited_by_count":84,"area":"lr"},{"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":"2503.06661","title":"AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP","created":"2025-03-09","cited_by_count":73,"area":null},{"id":"2303.17811","title":"Zero-shot Referring Image Segmentation with Global-Local Context Features","created":"2023-03-31","cited_by_count":61,"area":null},{"id":"2404.07990","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","created":"2024-04-11","cited_by_count":61,"area":null},{"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":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2306.05392","title":"Modular Visual Question Answering via Code Generation","created":"2023-06-08","cited_by_count":48,"area":null},{"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":"2307.12813","title":"Described Object Detection: Liberating Object Detection with Flexible Expressions","created":"2023-07-24","cited_by_count":40,"area":null},{"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":"2407.20171","title":"Diffusion Feedback Helps CLIP See Better","created":"2024-07-29","cited_by_count":38,"area":"diffusion"},{"id":"2304.04521","title":"GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection","created":"2023-04-10","cited_by_count":36,"area":null},{"id":"2409.17531","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","created":"2024-09-26","cited_by_count":36,"area":null},{"id":"2305.08685","title":"CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding","created":"2023-05-15","cited_by_count":35,"area":null},{"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":"2303.00040","title":"Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training","created":"2023-02-28","cited_by_count":32,"area":null},{"id":"2404.13400","title":"HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding","created":"2024-04-20","cited_by_count":31,"area":null},{"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":"2407.14563","title":"Learning Visual Grounding from Generative Vision and Language Model","created":"2024-07-18","cited_by_count":27,"area":null},{"id":"2404.06362","title":"Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2403.13805","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","created":"2024-03-20","cited_by_count":24,"area":null},{"id":"2404.11998","title":"Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation","created":"2024-04-18","cited_by_count":23,"area":null},{"id":"2311.05779","title":"Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter","created":"2023-11-09","cited_by_count":22,"area":null},{"id":"2311.17048","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","created":"2023-11-28","cited_by_count":21,"area":null},{"id":"2311.03354","title":"CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding","created":"2023-11-06","cited_by_count":20,"area":null},{"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":"2311.15773","title":"Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation","created":"2023-11-27","cited_by_count":19,"area":"diffusion"},{"id":"2502.00392","title":"RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes","created":"2025-02-01","cited_by_count":19,"area":null},{"id":"2308.09778","title":"Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models","created":"2023-08-18","cited_by_count":18,"area":"lr"},{"id":"2403.12884","title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","created":"2024-03-19","cited_by_count":18,"area":"lr"},{"id":"2406.18722","title":"Towards Open-World Grasping with Large Vision-Language Models","created":"2024-06-26","cited_by_count":15,"area":"mllm"},{"id":"2410.20155","title":"Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models","created":"2024-10-26","cited_by_count":15,"area":"diffusion"},{"id":"2504.00356","title":"Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation","created":"2025-04-01","cited_by_count":14,"area":null},{"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":"2410.02244","title":"Visual Prompting in LLMs for Enhancing Emotion Recognition","created":"2024-10-03","cited_by_count":12,"area":null},{"id":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2205.09256","title":"Training Vision-Language Transformers from Captions","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2305.17903","title":"Deeply Coupled Cross-Modal Prompt Learning","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2401.00094","title":"Generating Enhanced Negatives for Training Language-Based Object Detectors","created":"2023-12-29","cited_by_count":11,"area":null},{"id":"2403.04321","title":"Discriminative Probing and Tuning for Text-to-Image Generation","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2412.02402","title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","created":"2024-12-03","cited_by_count":11,"area":null},{"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":"2305.13876","title":"Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans","created":"2023-05-23","cited_by_count":10,"area":null},{"id":"2311.12890","title":"De-fine: Decomposing and Refining Visual Programs with Auto-Feedback","created":"2023-11-21","cited_by_count":10,"area":null},{"id":"2508.00230","title":"Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri--Rao Product","created":"2025-08-01","cited_by_count":10,"area":null},{"id":"2411.17041","title":"Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM","created":"2024-11-26","cited_by_count":9,"area":"diffusion"},{"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":"2305.19108","title":"DisCLIP: Open-Vocabulary Referring Expression Generation","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2407.05578","title":"FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance","created":"2024-07-08","cited_by_count":8,"area":null},{"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":"2601.06874","title":"MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation","created":"2026-01-11","cited_by_count":8,"area":null},{"id":"2211.02178","title":"Zero-shot Video Moment Retrieval With Off-the-Shelf Models","created":"2022-11-03","cited_by_count":7,"area":null},{"id":"2504.17224","title":"Visual and Textual Prompts in VLLMs for Enhancing Emotion Recognition","created":"2025-04-24","cited_by_count":7,"area":null},{"id":"2505.23769","title":"TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models","created":"2025-05-29","cited_by_count":7,"area":null},{"id":"2407.02389","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","created":"2024-07-02","cited_by_count":6,"area":null},{"id":"2312.15844","title":"Learning-To-Rank Approach for Identifying Everyday Objects Using a Physical-World Search Engine","created":"2023-12-26","cited_by_count":5,"area":null},{"id":"2507.05515","title":"LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants","created":"2025-07-07","cited_by_count":5,"area":"lr"},{"id":"2511.04601","title":"PixCLIP: Achieving Fine-grained Visual Language Understanding via Any-granularity Pixel-Text Alignment Learning","created":"2025-11-06","cited_by_count":5,"area":null},{"id":"2301.08913","title":"Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning","created":"2023-01-21","cited_by_count":4,"area":"lr"},{"id":"2302.06072","title":"Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation","created":"2023-02-13","cited_by_count":4,"area":null},{"id":"2405.07451","title":"CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering","created":"2024-05-13","cited_by_count":4,"area":"lr"},{"id":"2305.17369","title":"Modularized Zero-shot VQA with Pre-trained Models","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2307.00862","title":"UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding","created":"2023-07-03","cited_by_count":3,"area":"lr"},{"id":"2403.16539","title":"Data-Efficient 3D Visual Grounding via Order-Aware Referring","created":"2024-03-25","cited_by_count":3,"area":null},{"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":"2205.12089","title":"Sim-To-Real Transfer of Visual Grounding for Human-Aided Ambiguity Resolution","created":"2022-05-24","cited_by_count":2,"area":null},{"id":"2310.12147","title":"InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions","created":"2023-10-18","cited_by_count":2,"area":null},{"id":"2407.20034","title":"MaskInversion: Localized Embeddings via Optimization of Explainability Maps","created":"2024-07-29","cited_by_count":2,"area":"mllm"},{"id":"2408.16700","title":"GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models","created":"2024-08-29","cited_by_count":2,"area":null},{"id":"2410.07394","title":"Structured Spatial Reasoning with Open Vocabulary Object Detectors","created":"2024-10-09","cited_by_count":2,"area":"lr"},{"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":"2603.04803","title":"Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation","created":"2026-03-05","cited_by_count":2,"area":null},{"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":"2210.00858","title":"Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach","created":"2022-10-03","cited_by_count":1,"area":"lr"},{"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":"2308.09779","title":"EAVL: Explicitly Align Vision and Language for Referring Image Segmentation","created":"2023-08-18","cited_by_count":1,"area":null},{"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":"2601.00359","title":"Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers","created":"2026-01-01","cited_by_count":1,"area":null},{"id":"2601.12781","title":"VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension","created":"2026-01-19","cited_by_count":1,"area":"lr"},{"id":"2603.14880","title":"RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation","created":"2026-03-16","cited_by_count":1,"area":null}],"next_cursor":"100"}