embodied agent

Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks WACV 2025 ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination ICLR 2025 LVLMs are Bad at Overhearing Human Referential Communication EMNLP 2025 Mechanistic Interpretability for Steering Vision-Language-Action Models CoRL 2025 MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents ICLR 2025 MMInA: Benchmarking Multihop Multimodal Internet Agents ACL 2025 MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory ICLR 2025 Multi-Modal Grounded Planning and Efficient Replanning for Learning Embodied Agents with a Few Examples AAAI 2025 Multimodal LLM Guided Exploration and Active Mapping using Fisher Information ICCV 2025 NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM ACL 2025 NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains ICLR 2025 Open-World Planning via Lifted Regression with LLM-Inferred Affordances for Embodied Agents ACL 2025 Orchestrating Emergent Storytelling with Embodied Multi-Agent Systems NeurIPS 2025 PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding ICLR 2025 Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language Navigation AAAI 2025 RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints ICCV 2025 Scene-LLM: Extending Language Model for 3D Visual Reasoning WACV 2025 Scene Map-based Prompt Tuning for Navigation Instruction Generation CVPR 2025 TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making EMNLP 2025 Towards Autonomous Micromobility through Scalable Urban Simulation CVPR 2025 Trial-Oriented Visual Rearrangement ICCV 2025 UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent ICML 2025 VIVA+: Human-Centered Situational Decision-Making EMNLP 2025 VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks ICCV 2025 WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment AAAI 2025