Tsui-Wei Weng
- Papers
- 9
Cite
Notes
Only stored in your browser.
Authored papers
9Rethinking Crowd-Sourced Evaluation of Neuron Explanations
arXiv 2025
ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
arXiv 2025
Effective Skill Unlearning through Intervention and Abstention
arXiv 2025
Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
arXiv 2024
Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
arXiv 2024
Provably Robust Conformal Prediction with Improved Efficiency
arXiv 2024
Concept Bottleneck Large Language Models
arXiv 2024
Prediction without Preclusion: Recourse Verification with Reachable Sets
arXiv 2023
ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction
arXiv 2023
Affiliations
Frequent co-authors
10from 9 papers