Five works accepted to NeurIPS 2026 workshops
Published: 4 October 2026
We are pleased to share that five of our works have been accepted to NeurIPS 2026 workshops.
The accepted works span several of our current research directions, including the geometry of softmax attention, policy improvement, risk-sensitive decision-making, and AI-native research workflows.
These results mark the successful completion of QRS Research Academy, 2026 Fall #1, our inaugural cohort, in which members worked towards developing and submitting their first workshop papers. Contributors across the five accepted works include Yuhe S., Jianing Zhang, Yingzhi Tang, Shufang Chen, Xiaotong Li, Zimeng Wang, and Xinyue WU.
We look forward to presenting these works at NeurIPS 2026 and to advancing the research directions they represent. Further details on our research and programmes are available at qrsntu.org.
The accepted works
- Geometric Attention Fine-Tuning Is Representation-Relative: Autonomous ML Research with AI-Native Workflow
- PolicyAttention: Robustness and Failure Modes of Softmax Policy Improvement
- PolicyAttention: When Softmax Attention Becomes Policy Improvement
- Diverse Scenarios, Selective Evaluation: Certified Spectral-Risk Decisions under Costly Robustness Tests
- The Approximation Rank of Softmax Attention: Sharp Geometric Laws and Robust Interaction Dimension