{"list":"other","total":56,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"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":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2506.01844","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","created":"2025-06-02","cited_by_count":530},{"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":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410},{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"1903.01973","title":"Learning Latent Plans from Play","created":"2019-03-05","cited_by_count":316},{"id":"2601.16163","title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","created":"2026-01-22","cited_by_count":300},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158},{"id":"2507.16815","title":"ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning","created":"2025-07-22","cited_by_count":156},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136},{"id":"2407.05996","title":"Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals","created":"2024-07-08","cited_by_count":134},{"id":"2510.26583","title":"Emu3.5: Native Multimodal Models are World Learners","created":"2025-10-30","cited_by_count":132},{"id":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94},{"id":"2507.16746","title":"Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning","created":"2025-07-22","cited_by_count":84},{"id":"2510.13778","title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","created":"2025-10-15","cited_by_count":84},{"id":"1807.00652","title":"PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation","created":"2018-07-02","cited_by_count":58},{"id":"1511.09249","title":"On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models","created":"2015-11-30","cited_by_count":55},{"id":"2411.17762","title":"MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding","created":"2024-11-26","cited_by_count":44},{"id":"2410.15959","title":"Diffusion Transformer Policy","created":"2024-10-21","cited_by_count":41},{"id":"2207.05518","title":"Tracking Objects as Pixel-wise Distributions","created":"2022-07-12","cited_by_count":37},{"id":"2602.09849","title":"BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation","created":"2026-02-10","cited_by_count":30},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21},{"id":"2509.09666","title":"Unified Multimodal Models as Auto-Encoders","created":"2025-09-11","cited_by_count":13},{"id":"2605.08567","title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","created":"2026-05-09","cited_by_count":10},{"id":"2403.20002","title":"Grounding and Enhancing Grid-based Models for Neural Fields","created":"2024-03-29","cited_by_count":9},{"id":"2601.17756","title":"MV-S2V: Multi-View Subject-Consistent Video Generation","created":"2026-01-25","cited_by_count":9},{"id":"2512.22854","title":"ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning","created":"2025-12-28","cited_by_count":7},{"id":"2602.03045","title":"Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation","created":"2026-02-03","cited_by_count":7},{"id":"2605.22875","title":"RMA: an Agentic System for Research-Level Mathematical Problems","created":"2026-05-20","cited_by_count":7},{"id":"2012.12469","title":"Augmenting Policy Learning with Routines Discovered from a Single Demonstration","created":"2020-12-23","cited_by_count":6},{"id":"2602.19461","title":"Laplacian Multi-scale Flow Matching for Generative Modeling","created":"2026-02-23","cited_by_count":6},{"id":"2512.19020","title":"CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization","created":"2025-12-22","cited_by_count":5}],"next_cursor":null}