News & Accolades

2026

Co-organizing TrustNLP @ ACL'26, continuing the workshop series on trustworthy NLP.
Presented Amazon's work on Frontier Safety in AI at IIT Bombay and IIIT Delhi as part of the India AI Summit. Amazon signed the "Frontier AI Commitments" at the Summit; my team is responsible for building the technical foundation for Amazon's AI offerings under these commitments.
Amazon Science article featuring my team's work: Building trust into AI.
Amazon Science blog: How catastrophic is your LLM?
Red Hat blog: AI trust through open collaboration: A new chapter for responsible innovation.
Organized the Trusted AI Symposium 2026 in New York City, an invitation-only event bringing together academic and industry researchers on AI safety and governance.

Winner of the Agent X competition (2025).
Co-organized the SemEval Unlearning Challenge at ACL.
My team leads the Nova AI Challenge, supporting 10 universities annually on safety research.
Represented Amazon at the Frontier Model Forum and Partnership on AI.
Papers in NeurIPS: VMDT, Agentic Benchmarks, LLM Unlearning (workshop).
Papers in NAACL: Localizing and Deleting Toxic Memories in LLMs (Findings).
Papers in ICLR: Quantitative Certification of Bias in LLMs.
Papers in AAAI: MUNCH, K-Edit (Preventing and Detecting LLM Misinformation workshop).

Papers in EMNLP: FLIRT, Attribute Controlled Fine-tuning, Data Advisor, Self-contradictory Reasoning (Findings).
Papers in ACL: Tree-of-Traversals.
Papers in NAACL: Slang in LLMs, LLM Steerability, Pronoun Tokenization Parity (Findings), MICo (Findings), BELIEVE (TrustNLP workshop), Debiasing Image Captioning (TrustNLP workshop).
Papers in NeurIPS: LLM-PIEval (AdvML Frontiers workshop).
Papers in ICASSP: Partial Federated Learning (Trustworthy Speech Processing workshop).

Invited panelist at AI For Open Society @ KDD'23.
Papers in EMNLP: Controlled Generation Evaluation, Faithful Model Evaluation, INVITE (Findings), Coordinated Replay for Continual FL (Industry Track).
Papers in ACL: Resolving Ambiguities in Text-to-Image.
Papers in NeurIPS: JAB (Socially Responsible LM Research workshop).
Papers in KDD: FedMultimodal.
Papers in ACM FAccT: Centering Trans & Non-Binary Voices.
Papers in ICASSP: Self-healing via Error Detection, Catastrophic Forgetting in Continual FL.
Papers in ICDM: Fairness in Large Scale NLU (Industry Day), Privacy in the Time of LMs (Industry Day).
Papers in Interspeech: Sampling Bias in NLU Models.
Papers in IEEE SLT: Decoding Algorithms and Fairness.
Papers in CIKM: LLM Steerability toward Personas (Personalized Generative AI workshop).

Best PhD Thesis Pitch Award at USC (2016).
IEEE Signal Processing Society travel award to ICASSP 2016.
Winner of the Interspeech Paralinguistics Challenge (2015) — second consecutive win.
Phi Beta Kappa Alumni in Southern California Scholarship (2015).
Winner of the Interspeech Paralinguistics Challenge (2013).
Provost Fellowship at USC (2010–2014).
Info-USA Exchange Scholarship (2009).