{"list":"other","total":55,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"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":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"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":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382},{"id":"2505.07062","title":"Seed1.5-VL Technical Report","created":"2025-05-11","cited_by_count":373},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2509.20427","title":"Seedream 4.0: Toward Next-generation Multimodal Image Generation","created":"2025-09-24","cited_by_count":249},{"id":"2504.06256","title":"Transfer between Modalities with MetaQueries","created":"2025-04-08","cited_by_count":236},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206},{"id":"2501.07542","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","created":"2025-01-13","cited_by_count":206},{"id":"2505.23764","title":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence","created":"2025-05-29","cited_by_count":183},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163},{"id":"2411.07975","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","created":"2024-11-12","cited_by_count":163},{"id":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146},{"id":"2501.13926","title":"Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step","created":"2025-01-23","cited_by_count":131},{"id":"2504.02826","title":"Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing","created":"2025-04-03","cited_by_count":99},{"id":"2506.21458","title":"MindCube: Spatial Mental Modeling from Limited Views","created":"2025-06-26","cited_by_count":95},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89},{"id":"2505.11409","title":"Visual Planning: Let's Think Only with Images","created":"2025-05-16","cited_by_count":85},{"id":"2510.08558","title":"Agent Learning via Early Experience","created":"2025-10-09","cited_by_count":85},{"id":"2507.16746","title":"Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning","created":"2025-07-22","cited_by_count":84},{"id":"2510.27492","title":"ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning","created":"2025-10-30","cited_by_count":56},{"id":"2406.06485","title":"Can Language Models Serve as Text-Based World Simulators?","created":"2024-06-10","cited_by_count":52},{"id":"2502.16707","title":"Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation","created":"2025-02-23","cited_by_count":42},{"id":"2505.13934","title":"RLVR-World: Training World Models with Reinforcement Learning","created":"2025-05-20","cited_by_count":40},{"id":"2311.16093","title":"Visual cognition in multimodal large language models","created":"2023-11-27","cited_by_count":38},{"id":"2509.02722","title":"Planning with Reasoning using Vision Language World Model","created":"2025-09-02","cited_by_count":36},{"id":"2510.14958","title":"MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning","created":"2025-10-16","cited_by_count":35},{"id":"2509.24897","title":"RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark","created":"2025-09-29","cited_by_count":33},{"id":"2505.13886","title":"Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning","created":"2025-05-20","cited_by_count":32},{"id":"2309.10498","title":"A Configurable Library for Generating and Manipulating Maze Datasets","created":"2023-09-19","cited_by_count":31},{"id":"2510.13759","title":"Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark","created":"2025-10-15","cited_by_count":29},{"id":"2511.02779","title":"When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought","created":"2025-11-04","cited_by_count":21},{"id":"2511.16671","title":"Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation","created":"2025-11-20","cited_by_count":18},{"id":"2505.16770","title":"RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputs","created":"2025-05-22","cited_by_count":17},{"id":"2511.01163","title":"ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation","created":"2025-11-03","cited_by_count":13},{"id":"2511.22586","title":"Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization","created":"2025-11-27","cited_by_count":8}],"next_cursor":null}