pith. sign in

Diyi Yang

Identifiers

  • name variant Diyi Yang 0.60 · backfill

Papers (21)

  1. SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction cs.CL · 2026 · author #9
  2. Offloading Score: Measuring AI Reliance Through Counterfactual Workflows cs.SE · 2026 · author #6
  3. SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization cs.CR · 2026 · author #8
  4. Sycophantic AI makes human interaction feel more effortful and less satisfying over time cs.HC · 2026 · author #8
  5. Reflections and New Directions for Human-Centered Large Language Models cs.CL · 2026 · author #58
  6. ProgramBench: Can Language Models Rebuild Programs From Scratch? cs.SE · 2026 · author #11
  7. SWE-chat: Coding Agent Interactions From Real Users in the Wild cs.AI · 2026 · author #5
  8. Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment cs.CL · 2026 · author #3
  9. HorizonBench: Long-Horizon Personalization with Evolving Preferences cs.CL · 2026 · author #10
  10. Behavior Latticing: Inferring User Motivations from Unstructured Interactions cs.HC · 2026 · author #3
  11. Generative Experiences for Digital Mental Health Interventions: Evidence from a Randomized Study cs.HC · 2026 · author #4
  12. Verbalizing LLMs' assumptions to explain and control sycophancy cs.CL · 2026 · author #10
  13. CodeClash: Benchmarking Goal-Oriented Software Engineering cs.SE · 2025 · author #9
  14. Measuring and mitigating overreliance to build human-compatible AI cs.CY · 2025 · author #15
  15. Generative Interfaces for Language Models cs.CL · 2025 · author #5
  16. AI Behavioral Science cs.HC · 2025 · author #18
  17. Searching for Privacy Risks in LLM Agents via Simulation cs.CR · 2025 · author #2
  18. The Rise of AI Companions: Interaction with AI Companions and Psychological Well-being cs.HC · 2025 · author #5
  19. SWE-smith: Scaling Data for Software Engineering Agents cs.SE · 2025 · author #10
  20. A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration cs.CL · 2023 · author #5
  21. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models cs.CL · 2022 · author #116

Mentions

  • 2606.02540 #9 · arxiv_oai · confidence 0.70 Diyi Yang
  • 2509.13323 #18 · arxiv_oai · confidence 0.70 Diyi Yang
  • 2605.29392 #6 · arxiv_oai · confidence 0.70 Diyi Yang
  • 2310.02170 #5 · arxiv_oai · confidence 0.70 Diyi Yang
  • 2509.08010 #15 · arxiv_oai · confidence 0.70 Diyi Yang

Frequent Coauthors