{"total":23,"rows":[{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2305.14167","title":"DetGPT: Detect What You Need via Reasoning","created":"2023-05-23","cited_by_count":112,"area":"lr"},{"id":"2307.00329","title":"DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment","created":"2023-07-01","cited_by_count":61,"area":"lr"},{"id":"2501.06430","title":"Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs","created":"2025-01-11","cited_by_count":16,"area":"lr"},{"id":"2409.15451","title":"Tag Map: A Text-Based Map for Spatial Reasoning and Navigation with Large Language Models","created":"2024-09-23","cited_by_count":12,"area":"lr"},{"id":"2405.17201","title":"Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View","created":"2024-05-27","cited_by_count":7,"area":"lr"},{"id":"2305.16602","title":"Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning","created":"2023-05-26","cited_by_count":6,"area":"lr"},{"id":"2505.24025","title":"DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models","created":"2025-05-29","cited_by_count":6,"area":"lr"},{"id":"2507.06719","title":"A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding","created":"2025-07-09","cited_by_count":6,"area":"lr"},{"id":"2403.18252","title":"Beyond Embeddings: The Promise of Visual Table in Visual Reasoning","created":"2024-03-27","cited_by_count":5,"area":"lr"},{"id":"2407.13505","title":"Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation","created":"2024-07-18","cited_by_count":5,"area":"lr"},{"id":"2408.01942","title":"Visual Grounding for Object-Level Generalization in Reinforcement Learning","created":"2024-08-04","cited_by_count":4,"area":"lr"},{"id":"2412.01370","title":"Understanding Museum Exhibits using Vision-Language Reasoning","created":"2024-12-02","cited_by_count":4,"area":"lr"},{"id":"2310.19995","title":"Emotional Theory of Mind: Bridging Fast Visual Processing with Slow Linguistic Reasoning","created":"2023-10-30","cited_by_count":3,"area":"lr"},{"id":"2602.08735","title":"From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2510.16540","title":"Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions","created":"2025-10-18","cited_by_count":2,"area":"lr"},{"id":"2601.16538","title":"OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding","created":"2026-01-23","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":"2509.20077","title":"Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2509.21922","title":"Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial Understanding","created":"2025-09-26","cited_by_count":0,"area":"lr"},{"id":"2511.19315","title":"Rethinking Intermediate Representation for VLM-based Robot Manipulation","created":"2025-11-24","cited_by_count":0,"area":"lr"},{"id":"2511.21064","title":"OVOD-Agent: A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving Detection","created":"2025-11-26","cited_by_count":0,"area":"lr"},{"id":"2604.26250","title":"Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning","created":"2026-04-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}