embodied agents
AI systems or robots that interact with the physical world and have a physical presence. These agents learn from their environment and experiences, contributing to fields such as robotics and autonomous systems.
- 3EED: Ground Everything Everywhere in 3D
- Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation
- C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
- Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
- Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
- DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
- ESCA: Contextualizing Embodied Agents via Scene-Graph Generation
- EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
- EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
- HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning
- LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents
- Learning 3D Persistent Embodied World Models
- Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
- MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
- PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
- Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
- Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning
- Universal Visuo-Tactile Video Understanding for Embodied Interaction
- VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
- ViSPLA: Visual Iterative Self-Prompting for Language-Guided 3D Affordance Learning