{"list":"other","total":55,"rows":[{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"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":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"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":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230},{"id":"2501.07542","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","created":"2025-01-13","cited_by_count":206},{"id":"2505.23764","title":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence","created":"2025-05-29","cited_by_count":183},{"id":"2503.14489","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","created":"2025-03-18","cited_by_count":182},{"id":"2312.16217","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","created":"2023-12-24","cited_by_count":162},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2412.07825","title":"3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark","created":"2024-12-10","cited_by_count":139},{"id":"2503.22976","title":"From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D","created":"2025-03-29","cited_by_count":138},{"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":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114},{"id":"2506.03135","title":"OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models","created":"2025-06-03","cited_by_count":114},{"id":"2406.05756","title":"EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models","created":"2024-06-09","cited_by_count":107},{"id":"2503.01773","title":"Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas","created":"2025-03-03","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":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73},{"id":"2504.20024","title":"SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning","created":"2025-04-28","cited_by_count":68},{"id":"2408.02718","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","created":"2024-08-05","cited_by_count":67},{"id":"2509.06266","title":"Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes","created":"2025-09-08","cited_by_count":63},{"id":"2501.10074","title":"SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning","created":"2025-01-17","cited_by_count":62},{"id":"2503.12799","title":"Grounded Chain-of-Thought for Multimodal Large Language Models","created":"2025-03-17","cited_by_count":59},{"id":"2501.11858","title":"EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents","created":"2025-01-21","cited_by_count":57},{"id":"2601.00393","title":"NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos","created":"2026-01-01","cited_by_count":46},{"id":"2509.18905","title":"How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective","created":"2025-09-23","cited_by_count":43},{"id":"2503.17349","title":"Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models","created":"2025-03-21","cited_by_count":37},{"id":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33},{"id":"2509.02359","title":"Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture","created":"2025-09-02","cited_by_count":30},{"id":"2505.05456","title":"SITE: towards Spatial Intelligence Thorough Evaluation","created":"2025-05-08","cited_by_count":29},{"id":"2603.07145","title":"LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models","created":"2026-03-07","cited_by_count":28},{"id":"2311.13951","title":"MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria","created":"2023-11-23","cited_by_count":27},{"id":"2504.20648","title":"SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data","created":"2025-04-29","cited_by_count":21},{"id":"2510.08673","title":"Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation","created":"2025-10-09","cited_by_count":19},{"id":"2308.09778","title":"Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models","created":"2023-08-18","cited_by_count":18},{"id":"2602.14941","title":"AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories","created":"2026-02-16","cited_by_count":15},{"id":"2601.15284","title":"Walk through Paintings: Egocentric World Models from Internet Priors","created":"2026-01-21","cited_by_count":14},{"id":"2508.03232","title":"CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios","created":"2025-08-05","cited_by_count":11},{"id":"2512.07733","title":"SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery","created":"2025-12-08","cited_by_count":11},{"id":"2511.01618","title":"Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models","created":"2025-11-03","cited_by_count":10},{"id":"2510.00855","title":"Can World Models Benefit VLMs for World Dynamics?","created":"2025-10-01","cited_by_count":9},{"id":"2602.00181","title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","created":"2026-01-30","cited_by_count":9},{"id":"2508.08199","title":"Generalizable Operating Room Expert with Multimodal Enhancement","created":"2025-08-11","cited_by_count":7},{"id":"2603.23404","title":"Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning","created":"2026-03-24","cited_by_count":6},{"id":"2507.12391","title":"Assessing the Value of Visual Input: A Benchmark of Multimodal Large Language Models for Robotic Path Planning","created":"2025-07-16","cited_by_count":4}],"next_cursor":null}