{"total":55,"rows":[{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114,"area":"mllm"},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73,"area":"mllm"},{"id":"2409.09788","title":"Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models","created":"2024-09-15","cited_by_count":54,"area":"lr"},{"id":"2510.17269","title":"FineVision: Open Data Is All You Need","created":"2025-10-20","cited_by_count":53,"area":"mllm"},{"id":"2106.02112","title":"Finding and Fixing Spurious Patterns with Explanations","created":"2021-06-03","cited_by_count":38,"area":null},{"id":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"id":"2509.17664","title":"SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models","created":"2025-09-22","cited_by_count":25,"area":"mllm"},{"id":"2505.17012","title":"SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence","created":"2025-05-22","cited_by_count":24,"area":"mllm"},{"id":"2506.21876","title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation","created":"2025-06-27","cited_by_count":24,"area":"wm"},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20,"area":null},{"id":"2505.19015","title":"Can Multimodal Large Language Models Understand Spatial Relations?","created":"2025-05-25","cited_by_count":20,"area":"mllm"},{"id":"2512.14856","title":"T5Gemma 2: Seeing, Reading, and Understanding Longer","created":"2025-12-16","cited_by_count":17,"area":null},{"id":"2305.11768","title":"Generating Visual Spatial Description via Holistic 3D Scene Understanding","created":"2023-05-19","cited_by_count":16,"area":null},{"id":"2309.04041","title":"Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models","created":"2023-09-07","cited_by_count":13,"area":"mllm"},{"id":"2507.07644","title":"FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations","created":"2025-07-10","cited_by_count":13,"area":"lr"},{"id":"2501.01243","title":"Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants","created":"2025-01-02","cited_by_count":12,"area":null},{"id":"2403.00729","title":"Can Transformers Capture Spatial Relations between Objects?","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2205.02671","title":"What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning","created":"2022-05-05","cited_by_count":10,"area":null},{"id":"2212.00921","title":"AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization","created":"2022-12-02","cited_by_count":10,"area":null},{"id":"2310.01636","title":"Adaptive Visual Scene Understanding: Incremental Scene Graph Generation","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2409.15454","title":"In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2104.12727","title":"2.5D Visual Relationship Detection","created":"2021-04-26","cited_by_count":7,"area":null},{"id":"2502.08317","title":"Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Prompting","created":"2025-02-12","cited_by_count":7,"area":"mllm"},{"id":"2210.11109","title":"Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2309.13610","title":"VisionKG: Unleashing the Power of Visual Datasets via Knowledge Graph","created":"2023-09-24","cited_by_count":5,"area":null},{"id":"2309.06680","title":"STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning","created":"2023-09-13","cited_by_count":3,"area":"lr"},{"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":"2406.06028","title":"ReCon1M:A Large-scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagery","created":"2024-06-10","cited_by_count":3,"area":null},{"id":"2505.05515","title":"Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience","created":"2025-05-07","cited_by_count":3,"area":"agents"},{"id":"2607.04423","title":"Transferability Between Understanding and Generation in Unified Multimodal Models","created":"2026-07-05","cited_by_count":3,"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":"2601.10254","title":"NoReGeo: Non-Reasoning Geometry Benchmark","created":"2026-01-15","cited_by_count":2,"area":"lr"},{"id":"2606.22694","title":"SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding","created":"2026-06-21","cited_by_count":2,"area":"lr"},{"id":"2609.24727","title":"ReSTI: A Source-Grounded Audit and Repair of STI-Bench","created":"2026-09-21","cited_by_count":2,"area":null},{"id":"2410.15312","title":"Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image","created":"2024-10-20","cited_by_count":1,"area":null},{"id":"2605.09963","title":"Learning to Perceive \"Where\": Spatial Pretext Tasks for Robust Self-Supervised Learning","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.09368","title":"PhysScene: A Scene Graph Dataset for Scientific Visual Reasoning in Physics Experiments","created":"2026-06-08","cited_by_count":1,"area":"lr"},{"id":"2608.03631","title":"SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classification","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.20414","title":"StateSight: Benchmarking Latent Spatial-State Reconstruction in Vision-Language Models","created":"2026-08-15","cited_by_count":1,"area":"mllm"},{"id":"2104.00387","title":"Commonsense Spatial Reasoning for Visually Intelligent Agents","created":"2021-04-01","cited_by_count":0,"area":null},{"id":"2211.15566","title":"Neuro-Symbolic Spatio-Temporal Reasoning","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2508.06584","title":"Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolution","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2602.19357","title":"MentalBlackboard: Evaluating Spatial Visualization via Mathematical Transformations","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.16456","title":"Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relations","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2607.00020","title":"EmbodimentSemantic: A Spatial Scene-Graph Dataset and Benchmark for Vision-Language Models on Embodied Manipulation Trajectories","created":"2026-06-06","cited_by_count":0,"area":"mllm"},{"id":"2608.02892","title":"Modeling Scientific Experiment Scenes: Dataset and Model","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.14741","title":"PolyComp: A Polycube-based Benchmark for Compositional 3D Spatial Reasoning in Multimodal Models","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2608.15605","title":"AlloEgo-VLM: Disambiguating Allocentric and Egocentric Reference Frames in Vision-Language Models","created":"2026-08-16","cited_by_count":0,"area":"mllm"},{"id":"2609.17004","title":"Symmetry-Aware Likelihood-Orbit Aggregation for Selective Left-Right Claim Verification","created":"2026-09-15","cited_by_count":0,"area":"mllm"},{"id":"2609.26093","title":"RECAP: Relation Evidence Calibration for Detecting Spatial Relation Hallucinations in Vision-Language Models","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2609.32566","title":"Compositional Objectives: Learning Structure in Structure","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}