{"total":34,"rows":[{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668,"area":"lr"},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314,"area":"lr"},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279,"area":"lr"},{"id":"2407.04973","title":"LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts","created":"2024-07-06","cited_by_count":245,"area":"lr"},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"id":"2305.14167","title":"DetGPT: Detect What You Need via Reasoning","created":"2023-05-23","cited_by_count":112,"area":"lr"},{"id":"2407.12366","title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models","created":"2024-07-17","cited_by_count":98,"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":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2405.15973","title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement","created":"2024-05-24","cited_by_count":74,"area":"lr"},{"id":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57,"area":"lr"},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45,"area":"lr"},{"id":"2410.16162","title":"Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning","created":"2024-10-21","cited_by_count":34,"area":"lr"},{"id":"2302.00389","title":"Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications","created":"2023-02-01","cited_by_count":27,"area":"lr"},{"id":"2209.10326","title":"Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering","created":"2022-09-21","cited_by_count":25,"area":"lr"},{"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":"2205.00949","title":"Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering","created":"2022-05-02","cited_by_count":12,"area":"lr"},{"id":"2305.04530","title":"A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues","created":"2023-05-08","cited_by_count":11,"area":"lr"},{"id":"2210.12079","title":"Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?","created":"2022-10-21","cited_by_count":8,"area":"lr"},{"id":"2205.12616","title":"Guiding Visual Question Answering with Attention Priors","created":"2022-05-25","cited_by_count":7,"area":"lr"},{"id":"2405.00021","title":"SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials","created":"2024-02-22","cited_by_count":7,"area":"lr"},{"id":"2311.05298","title":"Improving Vision-and-Language Reasoning via Spatial Relations Modeling","created":"2023-11-09","cited_by_count":5,"area":"lr"},{"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":"2510.06243","title":"CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning","created":"2025-10-03","cited_by_count":5,"area":"lr"},{"id":"2510.19245","title":"See, Think, Act: Online Shopper Behavior Simulation with VLM Agents","created":"2025-10-22","cited_by_count":5,"area":"lr"},{"id":"2209.07000","title":"VIPHY: Probing \"Visible\" Physical Commonsense Knowledge","created":"2022-09-15","cited_by_count":4,"area":"lr"},{"id":"2305.02265","title":"A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text","created":"2023-05-03","cited_by_count":4,"area":"lr"},{"id":"2510.04141","title":"The Artificial Intelligence Cognitive Examination: A Survey on the Evolution of Multimodal Evaluation from Recognition to Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"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":"2503.03556","title":"Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation","created":"2025-03-05","cited_by_count":3,"area":"lr"},{"id":"2606.17678","title":"See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL","created":"2026-06-16","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":"2405.16860","title":"Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks","created":"2024-05-27","cited_by_count":0,"area":"lr"},{"id":"2607.09654","title":"Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models","created":"2026-07-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}