AI.info

Shijian Lu

Explore Shijian Lu on AI.info.

• 3D-Aware VLMs with Implicit and Explicit Geometries
• RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
• Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation
• LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
• Boosting Reasoning in Large Multimodal Models via Activation Replay
• A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models
• Spatial Preference Rewarding for MLLMs Spatial Understanding