{"total":42,"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":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517,"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":"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":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175,"area":"lr"},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136,"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":"2301.05226","title":"See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning","created":"2023-01-12","cited_by_count":51,"area":"lr"},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"id":"2312.02896","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","created":"2023-12-05","cited_by_count":41,"area":"lr"},{"id":"2503.19312","title":"ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning","created":"2025-03-25","cited_by_count":37,"area":"lr"},{"id":"2310.16035","title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","created":"2023-10-24","cited_by_count":33,"area":"lr"},{"id":"2312.07399","title":"Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales","created":"2023-12-12","cited_by_count":33,"area":"lr"},{"id":"2410.20482","title":"What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration","created":"2024-10-27","cited_by_count":31,"area":"lr"},{"id":"2406.09175","title":"ReMI: A Dataset for Reasoning with Multiple Images","created":"2024-06-13","cited_by_count":30,"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":"2401.03411","title":"GRAM: Global Reasoning for Multi-Page VQA","created":"2024-01-07","cited_by_count":23,"area":"lr"},{"id":"2403.16385","title":"Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA","created":"2024-03-25","cited_by_count":19,"area":"lr"},{"id":"2312.01714","title":"Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models","created":"2023-12-04","cited_by_count":18,"area":"lr"},{"id":"2310.05861","title":"Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models","created":"2023-10-09","cited_by_count":14,"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":"2502.20395","title":"R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts","created":"2025-02-27","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":"2403.01777","title":"NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision","created":"2024-03-04","cited_by_count":5,"area":"lr"},{"id":"2409.10719","title":"Benchmarking VLMs' Reasoning About Persuasive Atypical Images","created":"2024-09-16","cited_by_count":5,"area":"lr"},{"id":"2403.13801","title":"Natural Language as Policies: Reasoning for Coordinate-Level Embodied Control with LLMs","created":"2024-03-20","cited_by_count":4,"area":"lr"},{"id":"2411.07611","title":"Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models","created":"2024-11-12","cited_by_count":4,"area":"lr"},{"id":"2603.16737","title":"Retrieving Counterfactuals Improves Visual In-Context Learning","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2504.10786","title":"Visual Language Models show widespread visual deficits on neuropsychological tests","created":"2025-04-15","cited_by_count":3,"area":"lr"},{"id":"2601.01095","title":"NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding","created":"2026-01-03","cited_by_count":3,"area":"lr"},{"id":"2601.07645","title":"PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs","created":"2026-01-12","cited_by_count":3,"area":"lr"},{"id":"2307.16395","title":"Bridging the Gap: Exploring the Capabilities of Bridge-Architectures for Complex Visual Reasoning Tasks","created":"2023-07-31","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":"2309.15074","title":"Natural Language based Context Modeling and Reasoning for Ubiquitous Computing with Large Language Models: A Tutorial","created":"2023-09-24","cited_by_count":1,"area":"lr"},{"id":"2603.03590","title":"Social Norm Reasoning in Multimodal Language Models: An Evaluation","created":"2026-03-03","cited_by_count":1,"area":"lr"},{"id":"2310.18369","title":"Apollo: Zero-shot MultiModal Reasoning with Multiple Experts","created":"2023-10-25","cited_by_count":0,"area":"lr"},{"id":"2506.16701","title":"Language-driven Description Generation and Common Sense Reasoning for Video Action Recognition","created":"2025-06-20","cited_by_count":0,"area":"lr"},{"id":"2602.11860","title":"Talk2DM: Enabling Natural Language Querying and Commonsense Reasoning for Vehicle-Road-Cloud Integrated Dynamic Maps with Large Language Models","created":"2026-02-12","cited_by_count":0,"area":"lr"},{"id":"2607.06445","title":"Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2609.20235","title":"Scene-Q: Confidence-Aware Coarse-to-Fine Querying of 3D Scenes with Selective VLM Reasoning","created":"2026-07-28","cited_by_count":0,"area":"lr"},{"id":"2610.00825","title":"Align Then Reason: A Multimodal Lip-Sync Judge for Dubbing","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}