About Me | Conferences | Publications | Grants | Mentoring | Service | Affiliation | CV

Talks and presentations

Conference attendance timeline

Upcoming:

• 2026 — Cybersecurity and Artificial Intelligence Fall 2026 Review Meeting — University of Texas at San Antonio, USA
  • Absolute Error is not Enough: Ranking Model Performance without Labels to Estimate Disparities at Scale — presenter
  • Embarrassingly Simple Access Control for Large Language Models — presenter
• 2026 — AACL-IJCNLP Main — Hengqin, China:
  • Absolute Error is not Enough: Ranking Model Performance without Labels to Estimate Disparities at Scale — presenter
  • Embarrassingly Simple Access Control for Large Language Models — presenter

Past:

• 2026 — Agentic AI Summit — University of California, Berkeley, USA
  • Access Control in Large Language Models via Latent Refusal Probing — presenter
• 2026 — ACL 2026 — San Diego, USA
  • PrivateNLP@ACL: Mechanistic Access Control in Large Language Models via Latent Refusal Probing — presenter
  • Findings of the ACL: Telling Speculative Stories to Help Humans Imagine the Harms of Healthcare AI — co-author
  • SRW@ACL: Understanding Clinical Cognitive Dialogues Using Large Language Models — co-author
• 2026 — Texas NLP Symposium — Texas A&M University, USA
  • Absolute Error Is Not Enough: Ranking Model Performance Without Labels — presenter
  • Understanding Clinical Cognitive Dialogues Using Large Language Models — co-author
• 2026 — NSF AI Spring School — UT San Antonio, USA — presenter
  • Mechanistic Access Control in Large Language Models via Latent Refusal Probing
• 2025 — ASU Cybersecurity and AI workshop — Angelo State University, USA — presenter
  • Can We Reliably Rank Model Performance across Domains without Labeled Data?
• 2024 — Data and AI Intensive Research with Rigor and Reproducibility — UM/JSU, USA — mentee
• 2024 — Inaugural Berkeley-Stanford Workshop on Veridical Data Science — UC Berkeley, USA — attendee