pith. sign in

Zhewei Yao

Identifiers

  • name variant Zhewei Yao 0.60 · backfill

Papers (13)

  1. Reinforcement Learning without Ground-Truth Solutions can Improve LLMs cs.LG · 2026 · author #7
  2. Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents cs.AI · 2026 · author #4
  3. Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents cs.CL · 2026 · author #4
  4. Residual Skill Optimization for Text-to-SQL Ensembles cs.CL · 2026 · author #9
  5. R$^3$-SQL: Ranking Reward and Resampling for Text-to-SQL cs.SE · 2026 · author #4
  6. Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning cs.AI · 2026 · author #6
  7. Residual Networks as Nonlinear Systems: Stability Analysis using Linearization cs.LG · 2019 · author #2
  8. JumpReLU: A Retrofit Defense Strategy for Adversarial Attacks cs.CR · 2019 · author #2
  9. On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent cs.LG · 2018 · author #3
  10. Inexact Non-Convex Newton-Type Methods math.OC · 2018 · author #1
  11. A hybrid adaptive MCMC algorithm in function spaces stat.CO · 2016 · author #3
  12. On an adaptive preconditioned Crank-Nicolson MCMC algorithm for infinite dimensional Bayesian inferences stat.CO · 2015 · author #2
  13. A TV-Gaussian prior for infinite-dimensional Bayesian inverse problems and its numerical implementations stat.ME · 2015 · author #1

Mentions

  • 2606.27369 #7 · arxiv_oai · confidence 0.70 Zhewei Yao
  • 2606.11680 #4 · arxiv_oai · confidence 0.70 Zhewei Yao
  • 1510.05239 #1 · backfill · confidence 0.70 Zhewei Yao
  • 1607.01458 #3 · arxiv_oai · confidence 0.70 Zhewei Yao
  • 1511.05838 #2 · arxiv_oai · confidence 0.70 Zhewei Yao
  • 2606.00547 #4 · arxiv_oai · confidence 0.70 Zhewei Yao
  • 2602.10090 #6 · arxiv_oai · confidence 0.70 Zhewei Yao
  • 2605.21792 #9 · arxiv_oai · confidence 0.70 Zhewei Yao

Frequent Coauthors