pith. sign in

Byeongchan Kim

Identifiers

  • name variant Byeongchan Kim 0.60 · backfill

Papers (4)

  1. Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning cs.LG · 2026 · author #2
  2. Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards cs.LG · 2026 · author #4
  3. Peng's Q($\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning cs.LG · 2026 · author #1
  4. RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings cs.LG · 2026 · author #1

Mentions

  • 2605.25740 #2 · arxiv_oai · confidence 0.70 Byeongchan Kim
  • 2605.20865 #4 · arxiv_oai · confidence 0.70 Byeongchan Kim

Frequent Coauthors