{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2505.07062","title":"Seed1.5-VL Technical Report","created":"2025-05-11","cited_by_count":373},{"id":"2303.15361","title":"A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts","created":"2023-03-27","cited_by_count":359},{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217},{"id":"2209.07522","title":"Test-Time Training with Masked Autoencoders","created":"2022-09-15","cited_by_count":212},{"id":"1610.06258","title":"Using Fast Weights to Attend to the Recent Past","created":"2016-10-20","cited_by_count":170},{"id":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169},{"id":"2505.20279","title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","created":"2025-05-26","cited_by_count":166},{"id":"2312.16217","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","created":"2023-12-24","cited_by_count":162},{"id":"2504.01805","title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","created":"2025-04-02","cited_by_count":159},{"id":"2506.09965","title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","created":"2025-06-11","cited_by_count":136},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130},{"id":"2411.07279","title":"The Surprising Effectiveness of Test-Time Training for Few-Shot Learning","created":"2024-11-11","cited_by_count":96},{"id":"2506.21458","title":"MindCube: Spatial Mental Modeling from Limited Views","created":"2025-06-26","cited_by_count":95},{"id":"2510.08531","title":"SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models","created":"2025-10-09","cited_by_count":90},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89},{"id":"2503.23765","title":"STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?","created":"2025-03-31","cited_by_count":79},{"id":"2501.12352","title":"Test-time regression: a unifying framework for designing sequence models with associative memory","created":"2025-01-21","cited_by_count":74},{"id":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73},{"id":"2006.10726","title":"Tent: Fully Test-time Adaptation by Entropy Minimization","created":"2020-06-18","cited_by_count":69},{"id":"2510.18632","title":"Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views","created":"2025-10-21","cited_by_count":65},{"id":"2512.23675","title":"End-to-End Test-Time Training for Long Context","created":"2025-12-29","cited_by_count":62},{"id":"2506.18385","title":"InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models","created":"2025-06-23","cited_by_count":28},{"id":"2504.05646","title":"Lattice: Learning to Efficiently Compress the Memory","created":"2025-04-08","cited_by_count":19},{"id":"2505.12363","title":"Towards Visuospatial Cognition via Hierarchical Fusion of Visual Experts","created":"2025-05-18","cited_by_count":11},{"id":"2512.24331","title":"Spatial-aware Vision Language Model for Autonomous Driving","created":"2025-12-30","cited_by_count":4}],"next_cursor":null}