pith. sign in

Kimin Lee

Identifiers

  • name variant Kimin Lee 0.60 · backfill

Papers (13)

  1. Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases cs.AI · 2026 · author #3
  2. WarmPrior: Straightening Flow-Matching Policies with Temporal Priors cs.LG · 2026 · author #5
  3. Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy cs.LG · 2026 · author #4
  4. Entropy-Aware On-Policy Distillation of Language Models cs.LG · 2026 · author #8
  5. Latent Action Pretraining from Videos cs.RO · 2024 · author #12
  6. Aligning Text-to-Image Models using Human Feedback cs.LG · 2023 · author #1
  7. Decision Transformer: Reinforcement Learning via Sequence Modeling cs.LG · 2021 · author #4
  8. Robust Inference via Generative Classifiers for Handling Noisy Labels stat.ML · 2019 · author #1
  9. A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks stat.ML · 2018 · author #1
  10. Hierarchical Novelty Detection for Visual Object Recognition cs.CV · 2018 · author #2
  11. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples stat.ML · 2017 · author #1
  12. Confident Multiple Choice Learning cs.LG · 2017 · author #1
  13. Simplified Stochastic Feedforward Neural Networks cs.LG · 2017 · author #1

Mentions

  • 2605.27355 #3 · arxiv_oai · confidence 0.70 Kimin Lee
  • 2603.07079 #8 · arxiv_oai · confidence 0.70 Kimin Lee
  • 2106.01345 #4 · arxiv_oai · confidence 0.70 Kimin Lee

Frequent Coauthors