pith. sign in

Pang Wei Koh

Identifiers

  • name variant Pang Wei Koh 0.60 · backfill

Papers (15)

  1. JobBench: Aligning Agent Work With Human Will cs.AI · 2026 · author #20
  2. Deep Reasoning in General Purpose Agents via Structured Meta-Cognition cs.CL · 2026 · author #8
  3. EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics cs.AI · 2026 · author #10
  4. Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model cs.CL · 2026 · author #6
  5. Olmo 3 cs.CL · 2025 · author #64
  6. DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research cs.CL · 2025 · author #21
  7. Spurious Rewards: Rethinking Training Signals in RLVR cs.AI · 2025 · author #13
  8. 2 OLMo 2 Furious cs.CL · 2024 · author #24
  9. OLMoE: Open Mixture-of-Experts Language Models cs.CL · 2024 · author #22
  10. DataComp-LM: In search of the next generation of training sets for language models cs.LG · 2024 · author #52
  11. OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models cs.CV · 2023 · author #13
  12. On the Opportunities and Risks of Foundation Models cs.LG · 2021 · author #49
  13. Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization cs.LG · 2019 · author #2
  14. Inferring Multidimensional Rates of Aging from Cross-Sectional Data cs.LG · 2018 · author #2
  15. Certified Defenses for Data Poisoning Attacks cs.LG · 2017 · author #2

Mentions

  • 2605.26329 #20 · arxiv_oai · confidence 0.70 Pang Wei Koh
  • 2602.07120 #6 · arxiv_oai · confidence 0.70 Pang Wei Koh
  • 2511.19399 #21 · arxiv_oai · confidence 0.70 Pang Wei Koh
  • 2406.11794 #52 · arxiv_oai · confidence 0.70 Pang Wei Koh
  • 2409.02060 #22 · arxiv_oai · confidence 0.70 Pang Wei Koh
  • 2506.10947 #13 · arxiv_oai · confidence 0.70 Pang Wei Koh

Frequent Coauthors