Goto

Collaborating Authors

 Materials



Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents Zihao Wang

Neural Information Processing Systems

These additional behavior tokens will be augmented to the vocabulary of pretrained Multimodal Language Models. With this encoder, we then pack long-term multimodal interactions involving task instructions, memories, thoughts, observations, textual responses, behavior trajectories, etc .





Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation

Neural Information Processing Systems

Minerals in rocks, sediment in soil, dust on surfaces, infection on leaves, stains on fabrics, and foam in liquids are some of these almost infinite numbers of states and patterns.