{"list":"other","total":57,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"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":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497},{"id":"2403.18814","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","created":"2024-03-27","cited_by_count":365},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279},{"id":"2412.04454","title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","created":"2024-12-05","cited_by_count":278},{"id":"2403.02502","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","created":"2024-03-04","cited_by_count":197},{"id":"2508.07917","title":"MolmoAct: Action Reasoning Models that can Reason in Space","created":"2025-08-11","cited_by_count":197},{"id":"2505.18719","title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","created":"2025-05-24","cited_by_count":176},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157},{"id":"2407.08739","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","created":"2024-07-11","cited_by_count":113},{"id":"2505.19789","title":"What Can RL Bring to VLA Generalization? An Empirical Study","created":"2025-05-26","cited_by_count":108},{"id":"2506.03143","title":"GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents","created":"2025-06-03","cited_by_count":95},{"id":"2307.01848","title":"Embodied Task Planning with Large Language Models","created":"2023-07-04","cited_by_count":84},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71},{"id":"2506.13654","title":"Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning","created":"2025-06-16","cited_by_count":68},{"id":"2504.15271","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","created":"2025-04-21","cited_by_count":64},{"id":"2404.16635","title":"TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning","created":"2024-04-25","cited_by_count":52},{"id":"2402.08178","title":"LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents","created":"2024-02-13","cited_by_count":51},{"id":"2412.11974","title":"Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning","created":"2024-12-16","cited_by_count":47},{"id":"2403.13248","title":"Mora: Enabling Generalist Video Generation via A Multi-Agent Framework","created":"2024-03-20","cited_by_count":45},{"id":"2503.21696","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","created":"2025-03-27","cited_by_count":44},{"id":"2508.13998","title":"Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation","created":"2025-08-19","cited_by_count":38},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36},{"id":"2308.07241","title":"Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents","created":"2023-08-14","cited_by_count":33},{"id":"2310.06147","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","created":"2023-10-09","cited_by_count":20},{"id":"2505.19767","title":"RFTF: Reinforcement Fine-tuning for Embodied Agents with Temporal Feedback","created":"2025-05-26","cited_by_count":20},{"id":"2507.09160","title":"Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization","created":"2025-07-12","cited_by_count":19},{"id":"2310.02239","title":"MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens","created":"2023-10-03","cited_by_count":15},{"id":"2503.08525","title":"GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training","created":"2025-03-11","cited_by_count":14},{"id":"2505.22050","title":"Reinforced Reasoning for Embodied Planning","created":"2025-05-28","cited_by_count":12},{"id":"2505.24846","title":"MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning","created":"2025-05-30","cited_by_count":11},{"id":"2502.13131","title":"Rethinking Diverse Human Preference Learning through Principal Component Analysis","created":"2025-02-18","cited_by_count":10},{"id":"2404.15190","title":"Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following","created":"2024-04-21","cited_by_count":7},{"id":"2311.15649","title":"RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks","created":"2023-11-27","cited_by_count":3}],"next_cursor":null}