Michael Qizhe Shieh
- Papers
- 12
Cite
Notes
Only stored in your browser.
Authored papers
12ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
arXiv 2026
In-Context Reinforcement Learning for Tool Use in Large Language Models
arXiv 2026
Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
arXiv 2026
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
arXiv 2026
Long-Context Inference with Retrieval-Augmented Speculative Decoding
arXiv 2025
ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
arXiv 2025
MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use
arXiv 2025
Diffusion Language Models are Super Data Learners
arXiv 2025
Efficient Process Reward Model Training via Active Learning
arXiv 2025
Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction
arXiv 2025
NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
arXiv 2025
LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization
arXiv 2025
Affiliations
Frequent co-authors
10from 12 papers