AI.info

Kang Liu

Explore Kang Liu on AI.info.

• SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
• Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models
• MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning
• Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
• DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
• EPO: Diverse and Realistic Protein Ensemble Generation via Energy Preference Optimization
• SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention
• The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models
• Multilingual Knowledge Graph Completion via Efficient Multilingual Knowledge Sharing