IEEE

Perception Tokens Enhance Visual Reasoning in Multimodal Language Models

Abstract: Multimodal language models (MLMs) still face challenges in fundamental visual perception tasks where specialized models excel. Tasks requiring reasoning about 3D structures benefit from ...

Create simple UX for domain-specific languages with VS Code

Generic formats like JSON or XML are easier to version than forms. However, they were not originally intended to be ...
IEEE

HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models

Abstract: We introduce HOIGPT, a token-based generative method that unifies 3D hand-object interactions (HOI) perception and generation, offering the first comprehensive solution for captioning and ...