AI.info

Qing Li

Explore Qing Li on AI.info.

• V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval
• Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
• Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
• To Retrieve or To Think? Cross-Boundary Context Evolution for Multi-hop Complex Reasoning
• DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysis
• KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls
• MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models
• VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment