{"total":43,"rows":[{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603,"area":"lr"},{"id":"2403.16999","title":"Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning","created":"2024-03-25","cited_by_count":280,"area":"lr"},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222,"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":"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":"2412.03548","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","created":"2024-12-04","cited_by_count":71,"area":"lr"},{"id":"2305.02317","title":"Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings","created":"2023-05-03","cited_by_count":69,"area":"lr"},{"id":"2402.04236","title":"CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning","created":"2024-02-06","cited_by_count":67,"area":"lr"},{"id":"2312.03052","title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","created":"2023-12-05","cited_by_count":66,"area":"lr"},{"id":"2310.15166","title":"Large Language Models are Visual Reasoning Coordinators","created":"2023-10-23","cited_by_count":58,"area":"lr"},{"id":"2305.11490","title":"LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation","created":"2023-05-19","cited_by_count":57,"area":"lr"},{"id":"2305.14985","title":"IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models","created":"2023-05-24","cited_by_count":47,"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":"2503.07523","title":"VisRL: Intention-Driven Visual Perception via Reinforced Reasoning","created":"2025-03-10","cited_by_count":39,"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":"2310.16035","title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","created":"2023-10-24","cited_by_count":33,"area":"lr"},{"id":"2312.02433","title":"Lenna: Language Enhanced Reasoning Detection Assistant","created":"2023-12-05","cited_by_count":29,"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":"2507.23779","title":"Phi-Ground Tech Report: Advancing Perception in GUI Grounding","created":"2025-07-31","cited_by_count":25,"area":"lr"},{"id":"2311.11598","title":"Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions","created":"2023-11-20","cited_by_count":14,"area":"lr"},{"id":"2401.01974","title":"Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers","created":"2024-01-03","cited_by_count":14,"area":"lr"},{"id":"2405.20834","title":"Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning","created":"2024-05-31","cited_by_count":14,"area":"lr"},{"id":"2410.11087","title":"Locality Alignment Improves Vision-Language Models","created":"2024-10-14","cited_by_count":13,"area":"lr"},{"id":"2310.05872","title":"ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models","created":"2023-10-09","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":"2312.16279","title":"Cloud-Device Collaborative Learning for Multimodal Large Language Models","created":"2023-12-26","cited_by_count":11,"area":"lr"},{"id":"2508.05954","title":"Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents","created":"2025-08-08","cited_by_count":8,"area":"lr"},{"id":"2512.06581","title":"MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding","created":"2025-12-06","cited_by_count":8,"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":"2506.07778","title":"A Neurosymbolic Agent System for Compositional Visual Reasoning","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2305.03204","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","created":"2023-05-04","cited_by_count":3,"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":"2403.10037","title":"Knowledge Condensation and Reasoning for Knowledge-based VQA","created":"2024-03-15","cited_by_count":3,"area":"lr"},{"id":"2511.19516","title":"Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning","created":"2025-11-24","cited_by_count":1,"area":"lr"},{"id":"2601.04891","title":"Scaling Vision Language Models for Pharmaceutical Long Form Video Reasoning on Industrial GenAI Platform","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2601.12781","title":"VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension","created":"2026-01-19","cited_by_count":1,"area":"lr"},{"id":"2403.02581","title":"VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing","created":"2024-03-05","cited_by_count":0,"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":"2604.17889","title":"AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning","created":"2026-04-20","cited_by_count":0,"area":"lr"},{"id":"2605.03927","title":"StateVLM: A State-Aware Vision-Language Model for Robotic Affordance Reasoning","created":"2026-05-05","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":"2610.05630","title":"Atomic Visual Entailment: Enhancing Zero-Shot Vision-Language Reasoning through Atomic Fact Decomposition and Learned Selection","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}