Jian Gao

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vision-Language-Action policies.

The paper proposes Localized and Disentangled Knowledge Editing (LDKE), a framework that significantly improves knowledge editing in Multimodal Large Language Models by ensuring edits are both precise and generalize correctly to related contexts.

The paper introduces LingBot-World 2.0, an advanced version of a language model with unbounded interaction horizon, rapid response time, diverse interactive elements, and agentic harness integration.

This paper proposes an online method, M-OSVGP with GOIPS, for efficiently updating radio maps from streaming spectrum measurements.