PPaperPicks

Tsui-Wei Weng

17 papers at tracked venues · 11 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. Anti-Sensing: Defense Against Unauthorized Radar-Based Human Vital Sign Sensing with Physically Realizable Wearable Oscillators
  2. Concept Bottleneck Large Language Models
  3. Effective Skill Unlearning through Intervention and Abstention
  4. Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
  5. Interpretable Generative Models through Post-hoc Concept Bottlenecks
  6. Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
  7. SAND: Enhancing Open-Set Neuron Descriptions through Spatial Awareness
  8. ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
  9. Understanding Fixed Predictions via Confined Regions
  10. AND: Audio Network Dissection for Interpreting Deep Acoustic Models
  11. Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
  12. Interpretability-Guided Test-Time Adversarial Defense
  13. Linear Explanations for Individual Neurons
  14. One Step Closer to Unbiased Aleatoric Uncertainty Estimation
  15. Prediction without Preclusion: Recourse Verification with Reachable Sets
  16. Provably Robust Conformal Prediction with Improved Efficiency
  17. Towards Trustworthy Deep Learning
    AAAI 2024 · Tsui-Wei Lily Weng