{"list":"other","total":52,"rows":[{"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":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2504.19413","title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","created":"2025-04-28","cited_by_count":779},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280},{"id":"2412.18194","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","created":"2024-12-24","cited_by_count":175},{"id":"2506.06326","title":"Memory OS of AI Agent","created":"2025-05-30","cited_by_count":150},{"id":"2410.08189","title":"SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation","created":"2024-10-10","cited_by_count":109},{"id":"2508.09736","title":"Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory","created":"2025-08-13","cited_by_count":97},{"id":"2312.06648","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","created":"2023-12-11","cited_by_count":88},{"id":"2601.01885","title":"Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents","created":"2026-01-05","cited_by_count":78},{"id":"2406.09400","title":"Yo'LLaVA: Your Personalized Language and Vision Assistant","created":"2024-06-13","cited_by_count":62},{"id":"2409.18794","title":"Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs","created":"2024-09-27","cited_by_count":62},{"id":"2310.11604","title":"Language Models as Zero-Shot Trajectory Generators","created":"2023-10-17","cited_by_count":60},{"id":"2403.14599","title":"MyVLM: Personalizing VLMs for User-Specific Queries","created":"2024-03-21","cited_by_count":58},{"id":"2601.03515","title":"Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents","created":"2026-01-07","cited_by_count":54},{"id":"2512.03627","title":"MemVerse: Multimodal Memory for Lifelong Learning Agents","created":"2025-12-03","cited_by_count":35},{"id":"2310.07968","title":"Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation","created":"2023-10-12","cited_by_count":31},{"id":"2502.11903","title":"MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation","created":"2025-02-17","cited_by_count":29},{"id":"2402.08546","title":"Grounding LLMs For Robot Task Planning Using Closed-loop State Feedback","created":"2024-02-13","cited_by_count":25},{"id":"2602.07624","title":"M2A: Multimodal Memory Agent with Dual-Layer Hybrid Memory for Long-Term Personalized Interactions","created":"2026-02-07","cited_by_count":25},{"id":"2410.13360","title":"RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models","created":"2024-10-17","cited_by_count":24},{"id":"2302.12927","title":"Robot Behavior-Tree-Based Task Generation with Large Language Models","created":"2023-02-24","cited_by_count":23},{"id":"2505.16348","title":"Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization","created":"2025-05-22","cited_by_count":19},{"id":"2602.23008","title":"Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization","created":"2026-02-26","cited_by_count":19},{"id":"2404.11027","title":"Empowering Large Language Models on Robotic Manipulation with Affordance Prompting","created":"2024-04-17","cited_by_count":17},{"id":"2402.17587","title":"Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation","created":"2024-02-25","cited_by_count":15},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14},{"id":"2506.18369","title":"RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models","created":"2025-06-23","cited_by_count":13},{"id":"2410.18195","title":"Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments","created":"2024-10-23","cited_by_count":11},{"id":"2404.02018","title":"Large Language Models for Orchestrating Bimanual Robots","created":"2024-04-02","cited_by_count":10},{"id":"2503.18623","title":"Training-Free Personalization via Retrieval and Reasoning on Fingerprints","created":"2025-03-24","cited_by_count":10},{"id":"2412.01250","title":"Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues","created":"2024-12-02","cited_by_count":8},{"id":"2409.20548","title":"Robi Butler: Multimodal Remote Interaction with a Household Robot Assistant","created":"2024-09-30","cited_by_count":6},{"id":"2512.20014","title":"Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Prompting","created":"2025-12-23","cited_by_count":6},{"id":"2603.15117","title":"MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledge","created":"2026-03-16","cited_by_count":5},{"id":"2509.19843","title":"PersONAL: Towards a Comprehensive Benchmark for Personalized Embodied Agents","created":"2025-09-24","cited_by_count":4},{"id":"2509.25139","title":"Vision-and-Language Navigation with Analogical Textual Descriptions in LLMs","created":"2025-09-29","cited_by_count":3},{"id":"2512.18987","title":"Affordance RAG: Hierarchical Multimodal Retrieval with Affordance-Aware Embodied Memory for Mobile Manipulation","created":"2025-12-22","cited_by_count":3},{"id":"2602.06459","title":"User-Centric Object Navigation: A Benchmark with Integrated User Habits for Personalized Embodied Object Search","created":"2026-02-06","cited_by_count":3},{"id":"2603.05697","title":"MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents","created":"2026-03-05","cited_by_count":3},{"id":"2307.00114","title":"A Personalized Household Assistive Robot that Learns and Creates New Breakfast Options through Human-Robot Interaction","created":"2023-06-30","cited_by_count":1}],"next_cursor":null}