{"list":"other","total":67,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"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":"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":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"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":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"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":"2602.15763","title":"GLM-5: from Vibe Coding to Agentic Engineering","created":"2026-02-17","cited_by_count":587},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326},{"id":"2601.16163","title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","created":"2026-01-22","cited_by_count":300},{"id":"2412.14803","title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","created":"2024-12-19","cited_by_count":289},{"id":"2603.19312","title":"LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels","created":"2026-03-13","cited_by_count":273},{"id":"2511.08544","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","created":"2025-11-11","cited_by_count":254},{"id":"2506.18871","title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","created":"2025-06-23","cited_by_count":253},{"id":"2512.13030","title":"Motus: A Unified Latent Action World Model","created":"2025-12-15","cited_by_count":251},{"id":"2504.05299","title":"SmolVLM: Redefining small and efficient multimodal models","created":"2025-04-07","cited_by_count":237},{"id":"2503.00200","title":"Unified Video Action Model","created":"2025-02-28","cited_by_count":205},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163},{"id":"2604.14148","title":"Seedance 2.0: Advancing Video Generation for World Complexity","created":"2026-04-15","cited_by_count":160},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151},{"id":"2509.09674","title":"SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning","created":"2025-09-11","cited_by_count":151},{"id":"2509.09372","title":"VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model","created":"2025-09-11","cited_by_count":145},{"id":"2512.15692","title":"mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs","created":"2025-12-17","cited_by_count":142},{"id":"2412.07825","title":"3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark","created":"2024-12-10","cited_by_count":139},{"id":"2603.17240","title":"GigaWorld-Policy: An Efficient Action-Centered World--Action Model","created":"2026-03-18","cited_by_count":139},{"id":"2604.15483","title":"${\\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities","created":"2026-04-16","cited_by_count":138},{"id":"2502.21257","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete","created":"2025-02-28","cited_by_count":135},{"id":"2510.26583","title":"Emu3.5: Native Multimodal Models are World Learners","created":"2025-10-30","cited_by_count":132},{"id":"2602.10098","title":"VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model","created":"2026-02-10","cited_by_count":118},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117},{"id":"2604.05014","title":"StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing","created":"2026-04-06","cited_by_count":112},{"id":"2503.20752","title":"Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models","created":"2025-03-26","cited_by_count":99},{"id":"2604.27393","title":"MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction","created":"2026-04-30","cited_by_count":78},{"id":"2605.00078","title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","created":"2026-04-30","cited_by_count":75},{"id":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68},{"id":"2510.00406","title":"VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators","created":"2025-10-01","cited_by_count":67},{"id":"2307.12698","title":"MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features","created":"2023-07-24","cited_by_count":57},{"id":"2501.09781","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","created":"2025-01-16","cited_by_count":43},{"id":"2510.10903","title":"Towards a Unified Understanding of Robot Manipulation: A Comprehensive Survey","created":"2025-10-13","cited_by_count":32},{"id":"2602.11832","title":"JEPA-VLA: Video Predictive Embedding is Needed for VLA Models","created":"2026-02-12","cited_by_count":24},{"id":"2602.01166","title":"Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models","created":"2026-02-01","cited_by_count":22},{"id":"2602.10102","title":"VideoWorld 2: Learning Transferable Knowledge from Real-world Videos","created":"2026-02-10","cited_by_count":12},{"id":"2603.21669","title":"PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing","created":"2026-03-23","cited_by_count":9},{"id":"2602.23058","title":"GeoWorld: Geometric World Models","created":"2026-02-26","cited_by_count":6},{"id":"2603.09121","title":"DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulation","created":"2026-03-10","cited_by_count":6},{"id":"2605.23128","title":"$\\pi_0$-EqM: Equilibrium Matching for Closed-Loop Vision-Language-Action Control","created":"2026-05-22","cited_by_count":3},{"id":"2606.00110","title":"General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling","created":"2026-05-27","cited_by_count":1},{"id":"2606.11221","title":"LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment","created":"2026-05-27","cited_by_count":1}],"next_cursor":null}