News
2026
- Aug 2026: Released From Interpretability to Control, a retrospective on six years of the TrustNLP Workshop.
- Jul 2026: Co-organized the 6th TrustNLP Workshop at ACL 2026 in San Diego.
- 2026: LH-Deception (ICLR 2026), on LLM deceptive behaviors in long-horizon interactions, in collaboration with Prof. Sharon Li’s group at UW–Madison, accepted.
2025
- May 2025: Co-organized the TrustNLP Workshop at NAACL 2025.
- Feb 2025: Served as Area Chair for ACL Rolling Review (ARR).
- 2025: Agentic Benchmarks (NeurIPS D&B 2025), on best practices for building rigorous agentic benchmarks, accepted.
- 2025: Released the Amazon Nova Technical Report (arXiv 2025); led Responsible AI quantitative evaluation for Amazon Nova.
2024
- 2024: Tree-of-Traversals (ACL 2024), on zero-shot reasoning with knowledge graphs, led by our intern Elan, accepted.
2023
- 2023: Resolving Ambiguities in Text-to-Image (ACL 2023), led by our intern Nina, accepted.
- 2023: Centering Trans & Non-Binary Voices (ACM FAccT 2023), led by our intern Elia, accepted.
2022
- May 2022: Three papers accepted at ACL 2022 (main and Findings): Intrinsic vs Extrinsic Fairness (ACL 2022), Counterfactual Role Reversal (ACL Findings 2022), and Prediction Sensitivity (ACL 2022).
- May 2022: Co-organized the TrustNLP Workshop at NAACL 2022.
2021
- Jul 2021: Co-organized the Responsible AI Workshop at KDD 2021.
- May 2021: Co-organized the TrustNLP Workshop at NAACL 2021.
- Jan 2021: BOLD (ACM FAccT 2021), on bias in open-ended language generation, accepted. Dataset: BOLD on GitHub.
2020
- Dec 2020: Panelist on AI fairness discussion at NeurIPS 2020: panel video.
- Oct 2020: Efficient NAS for Sentence-Pair Tasks (EMNLP Workshop 2020), led by our intern Ansel, accepted.
- Feb 2020: Embedded High-Dim Bayesian Optimization (MedIA 2020), accepted.
- Feb 2020: Successfully defended Ph.D.: Thesis (RIT 2020).
2019 and earlier
- Dec 2019: Joined Amazon Alexa NU-AI as Research Scientist.
- Jun 2019: Graph BO-VAE (MICCAI 2019), finalist for Young Scientist Award.
- Oct 2018: S2S-LSH (IEEE Sensors Letters / NeurIPS ML4H 2018), accepted.
- Sep 2018: Generative-Model Bayesian Optimization (MICCAI 2018), finalist for Young Scientist Award.