PPaperPicks

Ruixuan Liu

8 papers at tracked venues · 6 at CORE A* · active 20252026

Venues

Frequent coauthors

Papers

  1. Direct Token Optimization: A Self-Contained Approach to Large Language Model Unlearning
  2. Differentially Private Visual Learning with Public Subspace Augmented by Synthetic Data
  3. Eye-In-Finger: Smart Fingers for Delicate Assembly and Disassembly of LEGO
  4. Generating Physically Stable and Buildable Brick Structures from Text
  5. MultiSFL: Towards Accurate Split Federated Learning via Multi-Model Aggregation and Knowledge Replay
  6. Time-Optimal Trajectory Generation with Multi-level Continuous Kinodynamics Constraints
    IROS 2025 · Ruixuan Liu
  7. Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
  8. Towards hyperparameter-free optimization with differential privacy
    ICLR 2025 · Ruixuan Liu