AI.info

Qi Zhang

Explore Qi Zhang on AI.info.

• Controllable Generative Sandbox for Causal Inference
• ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing
• Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
• RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning
• Markovian Scale Prediction: A New Era of Visual Autoregressive Generation
• Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
• Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning
• SEMPO: Lightweight Foundation Models for Time Series Forecasting
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping