{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"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":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2402.12289","title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","created":"2024-02-19","cited_by_count":490},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2307.15189","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","created":"2023-07-27","cited_by_count":392},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2312.07488","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","created":"2023-12-12","cited_by_count":305},{"id":"2307.06135","title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","created":"2023-07-12","cited_by_count":294},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205},{"id":"2207.02595","title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","created":"2022-07-06","cited_by_count":179},{"id":"2501.03895","title":"LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token","created":"2025-01-07","cited_by_count":166},{"id":"1908.00375","title":"Quality Assessment of In-the-Wild Videos","created":"2019-08-01","cited_by_count":164},{"id":"2011.13544","title":"Patch-VQ: 'Patching Up' the Video Quality Problem","created":"2020-11-27","cited_by_count":147},{"id":"1803.01761","title":"Large-Scale Study of Perceptual Video Quality","created":"2018-03-05","cited_by_count":127},{"id":"2404.00308","title":"ST-LLM: Large Language Models Are Effective Temporal Learners","created":"2024-03-30","cited_by_count":126},{"id":"1904.06457","title":"YouTube UGC Dataset for Video Compression Research","created":"2019-04-13","cited_by_count":124},{"id":"2412.15208","title":"OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Driving","created":"2024-12-19","cited_by_count":93},{"id":"2303.14302","title":"VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining","created":"2023-03-24","cited_by_count":65},{"id":"2012.13936","title":"Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessment","created":"2020-12-27","cited_by_count":50},{"id":"2210.05357","title":"Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment","created":"2022-10-11","cited_by_count":50},{"id":"2305.12726","title":"Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach","created":"2023-05-22","cited_by_count":45},{"id":"2206.09853","title":"DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment","created":"2022-06-20","cited_by_count":41},{"id":"2403.11956","title":"Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment","created":"2024-03-18","cited_by_count":39},{"id":"2409.20063","title":"Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs","created":"2024-09-30","cited_by_count":39},{"id":"2507.07105","title":"4KAgent: Agentic Any Image to 4K Super-Resolution","created":"2025-07-09","cited_by_count":36},{"id":"2503.14607","title":"Can Large Vision Language Models Read Maps Like a Human?","created":"2025-03-18","cited_by_count":30},{"id":"2402.19276","title":"Modular Blind Video Quality Assessment","created":"2024-02-29","cited_by_count":23},{"id":"2412.04508","title":"Video Quality Assessment: A Comprehensive Survey","created":"2024-12-04","cited_by_count":15}],"next_cursor":null}