State of Embodied AI

Top papers

• Benchmarking Interaction, Beyond Policy: a Reproducible Benchmark for Collaborative Instance Object Navigation(8.0)
• Fast-WAM: Do World Action Models Need Test-time Future Imagination?(8.0)
• Seed2Scale: A Self-Evolving Data Engine for Embodied AI via Small to Large Model Synergy and Multimodal Evaluation(8.0)
• SVLL: Staged Vision-Language Learning for Physically Grounded Embodied Task Planning(8.0)
• GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning(7.0)
• RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization(7.0)
• V-CAGE: Context-Aware Generation and Verification for Scalable Long-Horizon Embodied Tasks(7.0)
• Policy-Guided World Model Planning for Language-Conditioned Visual Navigation(7.0)
• VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents(7.0)
• NavTrust: Benchmarking Trustworthiness for Embodied Navigation(7.0)
• GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents(7.0)
• See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning(7.0)
• Panoramic Affordance Prediction(7.0)
• pFedNavi: Structure-Aware Personalized Federated Vision-Language Navigation for Embodied AI(6.0)
• Enhancing Linguistic Generalization of VLA: Fine-Tuning OpenVLA via Synthetic Instruction Augmentation(6.0)
• Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning(6.0)
• On the Strengths and Weaknesses of Data for Open-set Embodied Assistance(5.0)
• From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models(3.0)