{"total":56,"rows":[{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479,"area":"lr"},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776,"area":"lr"},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706,"area":"lr"},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2202.04053","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","created":"2022-02-08","cited_by_count":230,"area":"lr"},{"id":"2406.19389","title":"OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding","created":"2024-06-27","cited_by_count":127,"area":"lr"},{"id":"2312.03661","title":"Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving","created":"2023-12-06","cited_by_count":123,"area":"lr"},{"id":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122,"area":"lr"},{"id":"2208.05358","title":"CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning","created":"2022-08-10","cited_by_count":120,"area":"lr"},{"id":"2504.07954","title":"Perception-R1: Pioneering Perception Policy with Reinforcement Learning","created":"2025-04-10","cited_by_count":120,"area":"lr"},{"id":"2212.00259","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","created":"2022-12-01","cited_by_count":92,"area":"lr"},{"id":"2203.15442","title":"Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding","created":"2022-03-29","cited_by_count":53,"area":"lr"},{"id":"2205.13803","title":"Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions","created":"2022-05-27","cited_by_count":34,"area":"lr"},{"id":"2411.17606","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","created":"2024-11-26","cited_by_count":33,"area":"lr"},{"id":"2505.23727","title":"PixelThink: Towards Efficient Chain-of-Pixel Reasoning","created":"2025-05-29","cited_by_count":28,"area":"lr"},{"id":"2410.18923","title":"SegLLM: Multi-round Reasoning Segmentation","created":"2024-10-24","cited_by_count":25,"area":"lr"},{"id":"2204.12037","title":"Causal Reasoning Meets Visual Representation Learning: A Prospective Study","created":"2022-04-26","cited_by_count":24,"area":"lr"},{"id":"2502.16161","title":"OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models","created":"2025-02-22","cited_by_count":23,"area":"lr"},{"id":"2410.18570","title":"Zero-shot Object Navigation with Vision-Language Models Reasoning","created":"2024-10-24","cited_by_count":19,"area":"lr"},{"id":"2310.10207","title":"Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World","created":"2023-10-16","cited_by_count":18,"area":"lr"},{"id":"2411.16425","title":"TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation","created":"2024-11-25","cited_by_count":15,"area":"lr"},{"id":"2202.12626","title":"Joint Answering and Explanation for Visual Commonsense Reasoning","created":"2022-02-25","cited_by_count":11,"area":"lr"},{"id":"2405.06232","title":"Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process","created":"2024-05-10","cited_by_count":11,"area":"lr"},{"id":"2306.07743","title":"V-LoL: A Diagnostic Dataset for Visual Logical Learning","created":"2023-06-13","cited_by_count":8,"area":"lr"},{"id":"2503.07503","title":"Think Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of Thoughts","created":"2025-03-10","cited_by_count":7,"area":"lr"},{"id":"2203.05186","title":"Suspected Object Matters: Rethinking Model's Prediction for One-stage Visual Grounding","created":"2022-03-10","cited_by_count":4,"area":"lr"},{"id":"2209.07000","title":"VIPHY: Probing \"Visible\" Physical Commonsense Knowledge","created":"2022-09-15","cited_by_count":4,"area":"lr"},{"id":"2403.16921","title":"PropTest: Automatic Property Testing for Improved Visual Programming","created":"2024-03-25","cited_by_count":4,"area":"lr"},{"id":"2507.11936","title":"A Survey of Deep Learning for Geometry Problem Solving","created":"2025-07-16","cited_by_count":4,"area":"lr"},{"id":"2301.13007","title":"EuclidNet: Deep Visual Reasoning for Constructible Problems in Geometry","created":"2022-12-27","cited_by_count":3,"area":"lr"},{"id":"2504.19627","title":"VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning","created":"2025-04-28","cited_by_count":3,"area":"lr"},{"id":"2510.27266","title":"Enhancing Trustworthy GUI Grounding via Self-Critiqued Reinforcement Learning","created":"2025-10-31","cited_by_count":3,"area":"lr"},{"id":"2210.14808","title":"Search for Concepts: Discovering Visual Concepts Using Direct Optimization","created":"2022-10-25","cited_by_count":2,"area":"lr"},{"id":"2302.02117","title":"Learning to Agree on Vision Attention for Visual Commonsense Reasoning","created":"2023-02-04","cited_by_count":2,"area":"lr"},{"id":"2302.14431","title":"Efficient Masked Autoencoders with Self-Consistency","created":"2023-02-28","cited_by_count":2,"area":"lr"},{"id":"2310.08148","title":"Open-Set Knowledge-Based Visual Question Answering with Inference Paths","created":"2023-10-12","cited_by_count":2,"area":"lr"},{"id":"2406.00872","title":"OLIVE: Object Level In-Context Visual Embeddings","created":"2024-06-02","cited_by_count":2,"area":"lr"},{"id":"2408.16296","title":"Rethinking Sparse Lexical Representations for Image Retrieval in the Age of Rising Multi-Modal Large Language Models","created":"2024-08-29","cited_by_count":2,"area":"lr"},{"id":"2412.17741","title":"Reasoning to Attend: Try to Understand How <SEG> Token Works","created":"2024-12-23","cited_by_count":2,"area":"lr"},{"id":"2511.15256","title":"GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning","created":"2025-11-19","cited_by_count":2,"area":"lr"},{"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":"2212.01639","title":"Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests","created":"2022-12-03","cited_by_count":1,"area":"lr"},{"id":"2307.08506","title":"Does Visual Pretraining Help End-to-End Reasoning?","created":"2023-07-17","cited_by_count":1,"area":"lr"},{"id":"2311.06386","title":"Towards A Unified Neural Architecture for Visual Recognition and Reasoning","created":"2023-11-10","cited_by_count":1,"area":"lr"},{"id":"2507.00754","title":"Enhancing Self-Supervised Visual Representation Learning via Low-Rank Adapted LLMs","created":"2025-07-01","cited_by_count":1,"area":"lr"},{"id":"2510.03441","title":"Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning","created":"2025-10-03","cited_by_count":1,"area":"lr"},{"id":"2601.02008","title":"XAI-MeD: Explainable Knowledge Guided Neuro-Symbolic Framework for Domain Generalization and Rare Class Detection in Medical Imaging","created":"2026-01-05","cited_by_count":1,"area":"lr"},{"id":"2403.20026","title":"FSMR: A Feature Swapping Multi-modal Reasoning Approach with Joint Textual and Visual Clues","created":"2024-03-29","cited_by_count":0,"area":"lr"},{"id":"2508.15243","title":"Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agent","created":"2025-08-21","cited_by_count":0,"area":"lr"},{"id":"2604.08232","title":"HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2606.18846","title":"From Bounding Boxes to Visual Reasoning: An On-Policy Data Annotation Tool for Vision-Language Models","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2607.24082","title":"Towards High-Level Semantic Intelligence","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2608.02470","title":"Grounding Agentic VLMs with Dedicated Segmentation for Fine-Grained Vehicle Damage Assessment","created":"2026-08-03","cited_by_count":0,"area":"lr"},{"id":"2608.28707","title":"ReVA: A Region-Aware Visual Assistant for Visually Grounded Question Answering","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2608.30758","title":"CheXGround: Anatomical Region Tokens for Grounded Longitudinal Chest X-ray Interpretation","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.32569","title":"OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents","created":"2026-09-26","cited_by_count":0,"area":"lr"}],"next_cursor":null}