AI.info

Jiaqi Li

Explore Jiaqi Li on AI.info.

• SenseNova-U1.5: Towards Native Unified Visual Intelligence
• LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
• PandaPose: 3D Human Pose Lifting from a Single Image via Propagating 2D Pose Prior to 3D Anchor Space
• Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
• Scaling Spatial Intelligence with Multimodal Foundation Models
• LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?
• Statistical Guarantees for High-Dimensional Stochastic Gradient Descent