{"total":83,"rows":[{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919,"area":"lr"},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602,"area":"lr"},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529,"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":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314,"area":"lr"},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293,"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":"2303.12501","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","created":"2023-03-22","cited_by_count":132,"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":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57,"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":"2508.02095","title":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","created":"2025-08-04","cited_by_count":46,"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":"2406.02030","title":"Multimodal Reasoning with Multimodal Knowledge Graph","created":"2024-06-04","cited_by_count":44,"area":"lr"},{"id":"2211.16492","title":"Abstract Visual Reasoning with Tangram Shapes","created":"2022-11-29","cited_by_count":43,"area":"lr"},{"id":"2203.17271","title":"Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?","created":"2022-03-31","cited_by_count":31,"area":"lr"},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"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":"2204.12037","title":"Causal Reasoning Meets Visual Representation Learning: A Prospective Study","created":"2022-04-26","cited_by_count":24,"area":"lr"},{"id":"2502.01969","title":"Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration","created":"2025-02-04","cited_by_count":23,"area":"lr"},{"id":"2307.06166","title":"Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning","created":"2023-07-12","cited_by_count":22,"area":"lr"},{"id":"2210.00312","title":"Multimodal Analogical Reasoning over Knowledge Graphs","created":"2022-10-01","cited_by_count":21,"area":"lr"},{"id":"2409.13729","title":"MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Model","created":"2024-09-10","cited_by_count":21,"area":"lr"},{"id":"2502.12425","title":"Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2025-02-18","cited_by_count":20,"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":"2410.12219","title":"OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities","created":"2024-10-16","cited_by_count":16,"area":"lr"},{"id":"2410.20883","title":"Improving Generalization in Visual Reasoning via Self-Ensemble","created":"2024-10-28","cited_by_count":15,"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":"2205.00949","title":"Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering","created":"2022-05-02","cited_by_count":12,"area":"lr"},{"id":"2503.08308","title":"Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework","created":"2025-03-11","cited_by_count":12,"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":"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":"2309.01256","title":"BDC-Adapter: Brownian Distance Covariance for Better Vision-Language Reasoning","created":"2023-09-03","cited_by_count":6,"area":"lr"},{"id":"2402.10543","title":"Strong hallucinations from negation and how to fix them","created":"2024-02-16","cited_by_count":6,"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":"2407.04212","title":"Smart Vision-Language Reasoners","created":"2024-07-05","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":"2405.07451","title":"CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering","created":"2024-05-13","cited_by_count":4,"area":"lr"},{"id":"2405.16934","title":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR","created":"2024-05-27","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":"2202.12162","title":"Measuring CLEVRness: Blackbox testing of Visual Reasoning Models","created":"2022-02-24","cited_by_count":3,"area":"lr"},{"id":"2210.07519","title":"Can Language Representation Models Think in Bets?","created":"2022-10-14","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":"2401.10712","title":"Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge","created":"2024-01-19","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":"2410.03062","title":"Image First or Text First? Optimising the Sequencing of Modalities in Large Language Model Prompting and Reasoning Tasks","created":"2024-10-04","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":"2504.10786","title":"Visual Language Models show widespread visual deficits on neuropsychological tests","created":"2025-04-15","cited_by_count":3,"area":"lr"},{"id":"2511.05017","title":"Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings","created":"2025-11-07","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":"2210.01258","title":"Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes","created":"2022-10-03","cited_by_count":2,"area":"lr"},{"id":"2210.10300","title":"Dense but Efficient VideoQA for Intricate Compositional Reasoning","created":"2022-10-19","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":"2310.08148","title":"Open-Set Knowledge-Based Visual Question Answering with Inference Paths","created":"2023-10-12","cited_by_count":2,"area":"lr"},{"id":"2403.11541","title":"Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation","created":"2024-03-18","cited_by_count":2,"area":"lr"},{"id":"2404.13847","title":"EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning","created":"2024-04-22","cited_by_count":2,"area":"lr"},{"id":"2410.07394","title":"Structured Spatial Reasoning with Open Vocabulary Object Detectors","created":"2024-10-09","cited_by_count":2,"area":"lr"},{"id":"2508.10337","title":"A Curriculum Learning Approach to Reinforcement Learning: Leveraging RAG for Multimodal Question Answering","created":"2025-08-14","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":"2212.10292","title":"Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?","created":"2022-12-20","cited_by_count":1,"area":"lr"},{"id":"2303.15006","title":"Curriculum Learning for Compositional Visual Reasoning","created":"2023-03-27","cited_by_count":1,"area":"lr"},{"id":"2410.13666","title":"VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2505.16974","title":"OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual Reasoning","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2512.05530","title":"MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models","created":"2025-12-05","cited_by_count":1,"area":"lr"},{"id":"2603.10978","title":"GroundCount: Grounding Vision-Language Models with Object Detection for Mitigating Counting Hallucinations","created":"2026-03-11","cited_by_count":1,"area":"lr"},{"id":"2606.06100","title":"HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2204.08027","title":"Attention Mechanism based Cognition-level Scene Understanding","created":"2022-04-17","cited_by_count":0,"area":"lr"},{"id":"2310.15585","title":"Multimodal Representations for Teacher-Guided Compositional Visual Reasoning","created":"2023-10-24","cited_by_count":0,"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":"2312.15021","title":"Towards a Unified Multimodal Reasoning Framework","created":"2023-12-22","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":"2505.07500","title":"Learning to Reason and Navigate: Parameter Efficient Action Planning with Large Language Models","created":"2025-05-12","cited_by_count":0,"area":"lr"},{"id":"2508.04350","title":"Chain of Questions: Guiding Multimodal Curiosity in Language Models","created":"2025-08-06","cited_by_count":0,"area":"lr"},{"id":"2603.27558","title":"Learning to See through Illumination Extremes with Event Streaming in Multimodal Large Language Models","created":"2026-03-29","cited_by_count":0,"area":"lr"},{"id":"2607.00434","title":"Information-Regularized Attention for Visual-Centric Reasoning","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2609.05257","title":"Commonsense Reasoning in Computer Vision: Foundations, Recent Advancements, and Future Directions","created":"2026-09-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}