{"list":"other","total":76,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"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":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"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":"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":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"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":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"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":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","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":"2403.05135","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","created":"2024-03-08","cited_by_count":475},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"2505.07062","title":"Seed1.5-VL Technical Report","created":"2025-05-11","cited_by_count":373},{"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":"2405.08748","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","created":"2024-05-14","cited_by_count":298},{"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":"2506.18871","title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","created":"2025-06-23","cited_by_count":253},{"id":"2506.15564","title":"Show-o2: Improved Native Unified Multimodal Models","created":"2025-06-18","cited_by_count":250},{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161},{"id":"2501.16411","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding","created":"2025-01-27","cited_by_count":160},{"id":"2502.04326","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","created":"2025-02-06","cited_by_count":155},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133},{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129},{"id":"2505.13032","title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","created":"2025-05-19","cited_by_count":117},{"id":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110},{"id":"2508.11737","title":"Ovis2.5 Technical Report","created":"2025-08-15","cited_by_count":108},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105},{"id":"2409.15272","title":"OmniBench: Towards The Future of Universal Omni-Language Models","created":"2024-09-23","cited_by_count":102},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95},{"id":"2512.16776","title":"Kling-Omni Technical Report","created":"2025-12-18","cited_by_count":71},{"id":"2506.23044","title":"Ovis-U1 Technical Report","created":"2025-06-29","cited_by_count":67},{"id":"2506.09344","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","created":"2025-06-11","cited_by_count":66},{"id":"2504.16074","title":"PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models","created":"2025-04-22","cited_by_count":61},{"id":"2502.12054","title":"PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning","created":"2025-02-17","cited_by_count":59},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59},{"id":"2505.19099","title":"SeePhys: Does Seeing Help Thinking? -- Benchmarking Vision-Based Physics Reasoning","created":"2025-05-25","cited_by_count":34},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34},{"id":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26},{"id":"2510.24821","title":"Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation","created":"2025-10-28","cited_by_count":22},{"id":"2510.13721","title":"NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching","created":"2025-10-15","cited_by_count":21},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21},{"id":"2512.19526","title":"QuantiPhy: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models","created":"2025-12-22","cited_by_count":20},{"id":"2507.04766","title":"ABench-Physics: Benchmarking Physical Reasoning in LLMs via High-Difficulty and Dynamic Physics Problems","created":"2025-07-07","cited_by_count":18},{"id":"2509.14033","title":"SAIL-VL2 Technical Report","created":"2025-09-17","cited_by_count":14},{"id":"2412.08580","title":"LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations","created":"2024-12-11","cited_by_count":12},{"id":"2510.09507","title":"PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs","created":"2025-10-10","cited_by_count":9},{"id":"2509.13805","title":"Towards a Physics Foundation Model","created":"2025-09-17","cited_by_count":8},{"id":"2512.12756","title":"FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoning","created":"2025-12-14","cited_by_count":5}],"next_cursor":null}