pith. sign in

Anca Dragan

Identifiers

  • name variant Anca Dragan 0.60 · backfill

Papers (15)

  1. Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs cs.AI · 2026 · author #3
  2. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety cs.AI · 2025 · author #10
  3. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities cs.CL · 2025 · author #463
  4. Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 cs.LG · 2024 · author #8
  5. Gemma 2: Improving Open Language Models at a Practical Size cs.CL · 2024 · author #184
  6. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context cs.CL · 2024 · author #631
  7. Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback cs.AI · 2023 · author #29
  8. Preferences Implicit in the State of the World cs.LG · 2019 · author #5
  9. The Assistive Multi-Armed Bandit cs.LG · 2019 · author #4
  10. Should Robots be Obedient? cs.AI · 2017 · author #3
  11. Translating Neuralese cs.CL · 2017 · author #2
  12. DART: Noise Injection for Robust Imitation Learning cs.LG · 2017 · author #4
  13. The Off-Switch Game cs.AI · 2016 · author #2
  14. Comparing Human-Centric and Robot-Centric Sampling for Robot Deep Learning from Demonstrations cs.RO · 2016 · author #7
  15. Functional Gradient Motion Planning in Reproducing Kernel Hilbert Spaces cs.RO · 2016 · author #2

Mentions

  • 2605.21602 #3 · arxiv_oai · confidence 0.70 Anca Dragan
  • 2507.11473 #10 · arxiv_oai · confidence 0.70 Anca Dragan

Frequent Coauthors