{"total":32,"rows":[{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883,"area":"lr"},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314,"area":"lr"},{"id":"2212.02746","title":"UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression","created":"2022-12-06","cited_by_count":137,"area":"lr"},{"id":"2212.10535","title":"A Survey of Deep Learning for Mathematical Reasoning","created":"2022-12-20","cited_by_count":124,"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":"2507.17520","title":"InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation","created":"2025-07-23","cited_by_count":72,"area":"lr"},{"id":"2401.04181","title":"Language-Conditioned Robotic Manipulation with Fast and Slow Thinking","created":"2024-01-08","cited_by_count":17,"area":"lr"},{"id":"2204.02380","title":"CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations","created":"2022-04-05","cited_by_count":16,"area":"lr"},{"id":"2212.13296","title":"VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challenges","created":"2022-12-26","cited_by_count":14,"area":"lr"},{"id":"2511.21861","title":"Towards a Foundation Model for Partial Differential Equations Across Physics Domains","created":"2025-11-26","cited_by_count":7,"area":"lr"},{"id":"2605.05126","title":"ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation","created":"2026-05-06","cited_by_count":6,"area":"lr"},{"id":"2507.03585","title":"Causal-SAM-LLM: Large Language Models as Causal Reasoners for Robust Medical Segmentation","created":"2025-07-04","cited_by_count":5,"area":"lr"},{"id":"2203.05186","title":"Suspected Object Matters: Rethinking Model's Prediction for One-stage Visual Grounding","created":"2022-03-10","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":"2208.00361","title":"One for All: One-stage Referring Expression Comprehension with Dynamic Reasoning","created":"2022-07-31","cited_by_count":3,"area":"lr"},{"id":"2211.01994","title":"lilGym: Natural Language Visual Reasoning with Reinforcement Learning","created":"2022-11-03","cited_by_count":3,"area":"lr"},{"id":"2503.14957","title":"Neuro Symbolic Knowledge Reasoning for Procedural Video Question Answering","created":"2025-03-19","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":"2312.07886","title":"Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AI","created":"2023-12-13","cited_by_count":2,"area":"lr"},{"id":"2605.10485","title":"VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models","created":"2026-05-11","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":"2212.01639","title":"Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests","created":"2022-12-03","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":"2506.01623","title":"MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer","created":"2025-06-02","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":"2207.02624","title":"Knowing Earlier what Right Means to You: A Comprehensive VQA Dataset for Grounding Relative Directions via Multi-Task Learning","created":"2022-07-06","cited_by_count":0,"area":"lr"},{"id":"2509.08126","title":"Attribute-based Object Grounding and Robot Grasp Detection with Spatial Reasoning","created":"2025-09-09","cited_by_count":0,"area":"lr"},{"id":"2607.16704","title":"Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation","created":"2026-07-18","cited_by_count":0,"area":"lr"},{"id":"2607.25961","title":"Knowledge-Guided Multimodal Reasoning over Interacting Streams for Video-Level Ambivalence and Hesitancy Recognition","created":"2026-07-28","cited_by_count":0,"area":"lr"},{"id":"2608.28762","title":"Inter-3D VQA: A Roadside Multimodal Benchmark for 3D Spatiotemporally Grounded Visual Question Answering","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.31103","title":"DepthEvidence: Unifying Metric Depth Prediction and Geometric Reasoning in Multimodal Language Models","created":"2026-09-25","cited_by_count":0,"area":"lr"}],"next_cursor":null}