{"total":59,"rows":[{"id":"2504.15485","title":"CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting","created":"2025-04-21","cited_by_count":38,"area":"lr"},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2412.00686","title":"LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models","created":"2024-12-01","cited_by_count":20,"area":"mllm"},{"id":"2506.01320","title":"Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models","created":"2025-06-02","cited_by_count":15,"area":"diffusion"},{"id":"2506.15368","title":"Open-World Object Counting in Videos","created":"2025-06-18","cited_by_count":11,"area":null},{"id":"2503.12460","title":"Exploring Contextual Attribute Density in Referring Expression Counting","created":"2025-03-16","cited_by_count":10,"area":null},{"id":"2504.09480","title":"Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation","created":"2025-04-13","cited_by_count":10,"area":"mllm"},{"id":"2508.00728","title":"YOLO-Count: Differentiable Object Counting for Text-to-Image Generation","created":"2025-08-01","cited_by_count":10,"area":null},{"id":"2512.23351","title":"CountGD++: Generalized Prompting for Open-World Counting","created":"2025-12-29","cited_by_count":8,"area":null},{"id":"2509.13939","title":"Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation","created":"2025-09-17","cited_by_count":7,"area":null},{"id":"2511.17722","title":"Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions","created":"2025-11-21","cited_by_count":6,"area":"mllm"},{"id":"2511.08048","title":"Generalized-Scale Object Counting with Gradual Query Aggregation","created":"2025-11-11","cited_by_count":5,"area":null},{"id":"2508.16644","title":"CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance","created":"2025-08-18","cited_by_count":4,"area":"diffusion"},{"id":"2504.11705","title":"FiGO: Fine-Grained Object Counting without Annotations","created":"2025-04-16","cited_by_count":2,"area":null},{"id":"2504.17395","title":"SDVPT: Semantic-Driven Visual Prompt Tuning for Open-World Object Counting","created":"2025-04-24","cited_by_count":2,"area":"mllm"},{"id":"2505.22850","title":"What is the Right Embedding Space for Contrastive Learning in Referring Expression Counting?","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2510.11117","title":"Demystifying Numerosity in Diffusion Models -- Limitations and Remedies","created":"2025-10-13","cited_by_count":2,"area":"diffusion"},{"id":"2602.11024","title":"Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2602.12774","title":"Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Counting","created":"2026-02-13","cited_by_count":2,"area":null},{"id":"2603.21229","title":"Plant Taxonomy Meets Plant Counting: A Fine-Grained, Taxonomic Dataset for Counting Hundreds of Plant Species","created":"2026-03-22","cited_by_count":2,"area":null},{"id":"2605.02752","title":"Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting","created":"2026-05-04","cited_by_count":2,"area":null},{"id":"2505.15398","title":"Expanding Zero-Shot Object Counting with Rich Prompts","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2508.10710","title":"CountCluster: Training-Free Object Quantity Guidance with Cross-Attention Map Clustering for Text-to-Image Generation","created":"2025-08-14","cited_by_count":1,"area":"diffusion"},{"id":"2510.19278","title":"D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation","created":"2025-10-22","cited_by_count":1,"area":"diffusion"},{"id":"2510.24374","title":"Decoupling What to Count and Where to See for Referring Expression Counting","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2511.12702","title":"Counting Through Occlusion: Framework for Open World Amodal Counting","created":"2025-11-16","cited_by_count":1,"area":null},{"id":"2512.03233","title":"Object Counting with GPT-4o and GPT-5: A Comparative Study","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2512.20153","title":"CoDi -- an exemplar-conditioned diffusion model for low-shot counting","created":"2025-12-23","cited_by_count":1,"area":"diffusion"},{"id":"2601.13871","title":"OCCAM: Class-Agnostic, Training-Free, Prior-Free and Multi-Class Object Counting","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2602.19432","title":"CountEx: Fine-Grained Counting via Exemplars and Exclusion","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.15470","title":"Automated Counting of Stacked Objects in Industrial Inspection","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2604.08704","title":"RS-OVC: Open-Vocabulary Counting for Remote-Sensing Data","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.10887","title":"Count Anything at Any Granularity","created":"2026-05-11","cited_by_count":1,"area":"mllm"},{"id":"2605.18063","title":"The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.30059","title":"From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.02139","title":"AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Counting","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.16826","title":"Spatially-Aware Class-Agnostic Object Counting","created":"2026-07-18","cited_by_count":1,"area":null},{"id":"2609.07884","title":"Are Image Generators Zero-Shot Perceivers? A Rigorous Evaluation","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2411.11357","title":"Text-guided Zero-Shot Object Localization","created":"2024-11-18","cited_by_count":0,"area":null},{"id":"2505.10737","title":"Automated Detection of Salvin's Albatrosses: Improving Deep Learning Tools for Aerial Wildlife Surveys","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2512.16415","title":"CountZES: Counting via Zero-Shot Exemplar Selection","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2605.01827","title":"Referring Multiple Regions with Large Multimodal Models via Contextual Latent Steering","created":"2026-05-03","cited_by_count":0,"area":"mllm"},{"id":"2605.30846","title":"Count Anything","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2605.31212","title":"Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.17561","title":"RT-Counter: Real-Time Text-Guided Open-Vocabulary Object Counting","created":"2026-06-16","cited_by_count":0,"area":"mllm"},{"id":"2606.17601","title":"Test-Time Training for Robust Text-Guided Open-Vocabulary Object Counting","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.17650","title":"MambaCount: Efficient Text-guided Open-vocabulary Object Counting with Spatial Sparse State Space Duality Block","created":"2026-06-16","cited_by_count":0,"area":"ssm"},{"id":"2606.20728","title":"VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.23835","title":"ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation","created":"2026-06-22","cited_by_count":0,"area":"mllm"},{"id":"2608.06236","title":"Depth-Guided Video Object Counting in Crowded Scenes","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.15425","title":"NumerosityVLM: A Cognitively Inspired Benchmark for Interpreting Numerosity Representations in Vision-Language Models","created":"2026-08-15","cited_by_count":0,"area":"mllm"},{"id":"2608.20621","title":"RECOUNT: Reference-guided Counting with Synthetic Visual Exemplars","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.23845","title":"Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.30247","title":"OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.04716","title":"Counting Beyond Instances: A Benchmark for Group-Individual Object Counting","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.07939","title":"Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.17613","title":"DualCount: Structurally Consistent Density and Point Modeling for Zero-Shot Object Counting","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.37003","title":"VesselBench-800K: A Large-scale Perception Benchmark for Multimodal Vessel Detection, Counting, and Density Estimation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40230","title":"EviRover: Reinforcing Agentic Perception Beyond a Glance","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}