{"list":"other","total":60,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"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},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274},{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244},{"id":"2305.13655","title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models","created":"2023-05-23","cited_by_count":243},{"id":"1910.10073","title":"Depth-Adaptive Transformer","created":"2019-10-22","cited_by_count":236},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232},{"id":"2310.05492","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","created":"2023-10-09","cited_by_count":223},{"id":"2501.07542","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","created":"2025-01-13","cited_by_count":206},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179},{"id":"2307.04087","title":"SVIT: Scaling up Visual Instruction Tuning","created":"2023-07-09","cited_by_count":162},{"id":"2406.17294","title":"Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models","created":"2024-06-25","cited_by_count":133},{"id":"2203.12667","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","created":"2022-03-22","cited_by_count":117},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106},{"id":"2410.07087","title":"Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology","created":"2024-10-09","cited_by_count":95},{"id":"2305.19148","title":"Mitigating Label Biases for In-context Learning","created":"2023-05-28","cited_by_count":89},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71},{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60},{"id":"2305.06590","title":"FactKG: Fact Verification via Reasoning on Knowledge Graphs","created":"2023-05-11","cited_by_count":57},{"id":"2402.12058","title":"Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models","created":"2024-02-19","cited_by_count":57},{"id":"2305.08281","title":"FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge","created":"2023-05-14","cited_by_count":55},{"id":"2410.09604","title":"EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment","created":"2024-10-12","cited_by_count":42},{"id":"2412.03679","title":"Evaluating Language Models as Synthetic Data Generators","created":"2024-12-04","cited_by_count":33},{"id":"2410.18798","title":"Distill Visual Chart Reasoning Ability from LLMs to MLLMs","created":"2024-10-24","cited_by_count":31},{"id":"2408.09429","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","created":"2024-08-18","cited_by_count":30},{"id":"2310.03269","title":"InstructProtein: Aligning Human and Protein Language via Knowledge Instruction","created":"2023-10-05","cited_by_count":28},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23},{"id":"2407.07053","title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model","created":"2024-07-09","cited_by_count":21},{"id":"2311.00287","title":"Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models","created":"2023-11-01","cited_by_count":20},{"id":"2310.05861","title":"Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models","created":"2023-10-09","cited_by_count":14},{"id":"2504.05571","title":"Knowledge-Instruct: Effective Continual Pre-training from Limited Data using Instructions","created":"2025-04-08","cited_by_count":12},{"id":"2407.03672","title":"A Survey of Data Synthesis Approaches","created":"2024-07-04","cited_by_count":9},{"id":"2407.02233","title":"Synthetic Multimodal Question Generation","created":"2024-07-02","cited_by_count":8},{"id":"2504.06245","title":"Underwater Robotic Simulators Review for Autonomous System Development","created":"2025-04-08","cited_by_count":4}],"next_cursor":null}