{"list":"other","total":163,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"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":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"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":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"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":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2106.06103","title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","created":"2021-06-11","cited_by_count":561},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437},{"id":"2207.14315","title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","created":"2022-07-28","cited_by_count":400},{"id":"2106.06909","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","created":"2021-06-13","cited_by_count":399},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388},{"id":"2105.04165","title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","created":"2021-05-10","cited_by_count":383},{"id":"1709.05522","title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","created":"2017-09-16","cited_by_count":373},{"id":"2505.07062","title":"Seed1.5-VL Technical Report","created":"2025-05-11","cited_by_count":373},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2407.05407","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","created":"2024-07-07","cited_by_count":334},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"2504.08837","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":323},{"id":"1710.07300","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","created":"2017-10-19","cited_by_count":319},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"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},{"id":"2406.02430","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","created":"2024-06-04","cited_by_count":300},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288},{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"2103.10213","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","created":"2021-03-18","cited_by_count":256},{"id":"1601.07140","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","created":"2016-01-26","cited_by_count":236},{"id":"2105.14517","title":"GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning","created":"2021-05-30","cited_by_count":228},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"2412.02612","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","created":"2024-12-03","cited_by_count":224},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2408.16725","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","created":"2024-08-29","cited_by_count":210},{"id":"1612.01840","title":"FMA: A Dataset For Music Analysis","created":"2016-12-06","cited_by_count":207},{"id":"2407.05361","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","created":"2024-07-07","cited_by_count":204},{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197},{"id":"2501.01957","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","created":"2025-01-03","cited_by_count":197},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"2501.17399","title":"MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs","created":"2025-01-29","cited_by_count":180},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161},{"id":"2406.11768","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","created":"2024-06-17","cited_by_count":156},{"id":"1810.12440","title":"TallyQA: Answering Complex Counting Questions","created":"2018-10-29","cited_by_count":153}],"next_cursor":"100"}