{"list":"other","total":73,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"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":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"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":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"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":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586},{"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":"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":"2402.14804","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","created":"2024-02-22","cited_by_count":526},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476},{"id":"2403.05135","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","created":"2024-03-08","cited_by_count":475},{"id":"2101.00390","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","created":"2021-01-02","cited_by_count":463},{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429},{"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":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2406.02430","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","created":"2024-06-04","cited_by_count":300},{"id":"2407.04973","title":"LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts","created":"2024-07-06","cited_by_count":245},{"id":"2504.06256","title":"Transfer between Modalities with MetaQueries","created":"2025-04-08","cited_by_count":236},{"id":"2509.16117","title":"DiffusionNFT: Online Diffusion Reinforcement with Forward Process","created":"2025-09-19","cited_by_count":230},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197},{"id":"2404.16006","title":"MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI","created":"2024-04-24","cited_by_count":193},{"id":"2406.09411","title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","created":"2024-06-13","cited_by_count":188},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144},{"id":"2501.05510","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","created":"2025-01-09","cited_by_count":142},{"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},{"id":"2502.11946","title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","created":"2025-02-17","cited_by_count":83},{"id":"2410.23266","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models","created":"2024-10-30","cited_by_count":73},{"id":"2506.09344","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","created":"2025-06-11","cited_by_count":66},{"id":"2502.05173","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","created":"2025-02-07","cited_by_count":65},{"id":"2407.01509","title":"MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs","created":"2024-07-01","cited_by_count":62},{"id":"2502.03930","title":"DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation","created":"2025-02-06","cited_by_count":57},{"id":"2504.07957","title":"MM-IFEngine: Towards Multimodal Instruction Following","created":"2025-04-10","cited_by_count":42},{"id":"2509.02020","title":"FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot","created":"2025-09-02","cited_by_count":35},{"id":"2411.06208","title":"IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization","created":"2024-11-09","cited_by_count":31},{"id":"2508.19205","title":"VibeVoice Technical Report","created":"2025-08-26","cited_by_count":29},{"id":"2510.06590","title":"Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer","created":"2025-10-08","cited_by_count":28},{"id":"2104.03006","title":"Librispeech Transducer Model with Internal Language Model Prior Correction","created":"2021-04-07","cited_by_count":26},{"id":"2503.05139","title":"Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs","created":"2025-03-07","cited_by_count":22},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19},{"id":"2503.14345","title":"MoonCast: High-Quality Zero-Shot Podcast Generation","created":"2025-03-18","cited_by_count":18},{"id":"2511.05516","title":"Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation","created":"2025-10-26","cited_by_count":17},{"id":"2507.08306","title":"M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning","created":"2025-07-11","cited_by_count":16},{"id":"2507.05727","title":"ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark","created":"2025-07-08","cited_by_count":15},{"id":"2509.18004","title":"WenetSpeech-Chuan: A Large-Scale Sichuanese Corpus with Rich Annotation for Dialectal Speech Processing","created":"2025-09-22","cited_by_count":8},{"id":"2507.09318","title":"ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching","created":"2025-07-12","cited_by_count":7},{"id":"2510.23541","title":"SoulX-Podcast: Towards Realistic Long-form Podcasts with Dialectal and Paralinguistic Diversity","created":"2025-10-27","cited_by_count":6},{"id":"2407.06157","title":"Temporal Grounding of Activities using Multimodal Large Language Models","created":"2024-05-30","cited_by_count":3},{"id":"2510.00499","title":"MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance","created":"2025-10-01","cited_by_count":3}],"next_cursor":null}