{"total":65,"rows":[{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625,"area":null},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297,"area":null},{"id":"2310.01218","title":"Making LLaMA SEE and Draw with SEED Tokenizer","created":"2023-10-02","cited_by_count":185,"area":null},{"id":"2306.15724","title":"REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction","created":"2023-06-27","cited_by_count":175,"area":null},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142,"area":null},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109,"area":null},{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90,"area":null},{"id":"2511.13719","title":"Scaling Spatial Intelligence with Multimodal Foundation Models","created":"2025-11-17","cited_by_count":82,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"area":null},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49,"area":null},{"id":"2306.01667","title":"Towards In-context Scene Understanding","created":"2023-06-02","cited_by_count":47,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2502.03566","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","created":"2025-02-05","cited_by_count":31,"area":null},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2505.05456","title":"SITE: towards Spatial Intelligence Thorough Evaluation","created":"2025-05-08","cited_by_count":29,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2305.07558","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","created":"2023-05-12","cited_by_count":25,"area":null},{"id":"2402.01749","title":"Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models","created":"2024-01-30","cited_by_count":23,"area":null},{"id":"2509.01106","title":"Robix: A Unified Model for Robot Interaction, Reasoning and Planning","created":"2025-09-01","cited_by_count":23,"area":null},{"id":"2601.21406","title":"Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation","created":"2026-01-29","cited_by_count":20,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2601.20354","title":"Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models","created":"2026-01-28","cited_by_count":16,"area":null},{"id":"2503.14503","title":"The Power of Context: How Multimodality Improves Image Super-Resolution","created":"2025-03-18","cited_by_count":15,"area":null},{"id":"2502.14906","title":"Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models","created":"2025-02-18","cited_by_count":14,"area":null},{"id":"2502.15786","title":"MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding","created":"2025-02-18","cited_by_count":14,"area":null},{"id":"2406.15955","title":"Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects","created":"2024-06-22","cited_by_count":13,"area":null},{"id":"2412.06322","title":"LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations","created":"2024-12-09","cited_by_count":13,"area":null},{"id":"2501.15065","title":"Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts","created":"2025-01-25","cited_by_count":13,"area":null},{"id":"2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","created":"2025-02-23","cited_by_count":13,"area":null},{"id":"2411.00394","title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2410.05090","title":"HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2305.14281","title":"Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2312.02249","title":"Recursive Visual Programming","created":"2023-12-04","cited_by_count":6,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2504.00691","title":"ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts","created":"2025-04-01","cited_by_count":5,"area":null},{"id":"2505.09952","title":"Task-Core Memory Management and Consolidation for Long-term Continual Learning","created":"2025-05-15","cited_by_count":4,"area":null},{"id":"2412.18224","title":"Expand VSR Benchmark for VLLM to Expertize in Spatial Rules","created":"2024-12-24","cited_by_count":3,"area":null},{"id":"2502.09460","title":"Metamorphic Testing for Pose Estimation Systems","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2311.10883","title":"Labeling Indoor Scenes with Fusion of Out-of-the-Box Perception Models","created":"2023-11-17","cited_by_count":2,"area":null},{"id":"2510.21160","title":"Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2607.21072","title":"Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text","created":"2026-07-23","cited_by_count":2,"area":null},{"id":"2609.24727","title":"ReSTI: A Source-Grounded Audit and Repair of STI-Bench","created":"2026-09-21","cited_by_count":2,"area":null},{"id":"2207.00590","title":"ViRel: Unsupervised Visual Relations Discovery with Graph-level Analogy","created":"2022-07-04","cited_by_count":1,"area":null},{"id":"2403.13666","title":"Grounding Spatial Relations in Text-Only Language Models","created":"2024-03-20","cited_by_count":1,"area":null},{"id":"2404.16365","title":"VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2410.15312","title":"Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image","created":"2024-10-20","cited_by_count":1,"area":null},{"id":"2509.23452","title":"FoR-SALE: Frame of Reference-guided Spatial Adjustment in LLM-based Diffusion Editing","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2605.09963","title":"Learning to Perceive \"Where\": Spatial Pretext Tasks for Robust Self-Supervised Learning","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.02449","title":"HLL: Can Agents Cross Humanity's Last Line of Verification?","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2609.19554","title":"VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2601.09613","title":"CogRail: Benchmarking VLMs in Cognitive Intrusion Perception for Intelligent Railway Transportation Systems","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2602.11615","title":"SkillRater: Untangling Capabilities in Multimodal Data","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2602.19357","title":"MentalBlackboard: Evaluating Spatial Visualization via Mathematical Transformations","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.04277","title":"VehAnchor: Metadata-Free Metric Scale Recovery from Vehicle Cues in Aerial Imagery","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.18714","title":"Semantic Generative Tuning for Unified Multimodal Models","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.22543","title":"MAPS: Multi-Anchor Projection Similarity for Joint Vision-Language Geo-Localization","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.14616","title":"SportD: How do VLMs physically strategize?","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.15299","title":"MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.17999","title":"Do Maps Still Matter for Machines: Revisiting the Role of Choropleth Maps in Foundation Model Spatial Understanding","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.05747","title":"GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2610.16441","title":"VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}