News & Accolades

2026

NeurIPS 2026
NeurIPS 2026 Papers
Accepted papers across NeurIPS tracks and workshops: Beyond Risky Activities: Bridging the Supervision Gap for Situational Risk Reasoning (Evaluations and Datasets Track poster), Adaptive Adversarial Evaluation: A Search--Freeze--Replay Tutorial (Education Track), and two AIWILD workshop posters: Are Your Agents Ready to Evolve? and RedInject.
Oct 22-23, 2026
USC Ming Hsieh ECE Emerging Changemaker Award
🏆 Received the ECE Emerging Changemaker Award during USC Ming Hsieh ECE's 20th Naming Anniversary. Certificate
Oct 9, 2026
COLM - Invited Talk
Invited speaker at AdvML-Frontiers × CoTMA workshop on multi-agent AI security.
Sep 2026
Frontier AI Safety & Public-Sector AI
Engaged with AI policy and public-sector leaders at Governing at the Speed of AI during UNGA and contributed to Amazon's updated Frontier Model Safety Framework.
Sep 8-12, 2026
ECCV
Papers: Compositional Privacy Risk Framework with VLMs and Video-Based Reward Modeling for Computer-Use Agents.
Aug 2026
EMNLP 2026 & TMLR
Three EMNLP 2026 papers accepted: UNISAF-Bench, SkillHarm 🏆 (Outstanding Paper Award), and PReMISE; CQ-Bench accepted at TMLR.
Aug 2026
MAA MathFest & IJCAI-ECAI
Panelist for Career Paths in Business, Industry, and Government at MAA MathFest; talk at the Workshop on Foundation Models for Social Good, co-located with IJCAI-ECAI 2026.
Jul 2-7, 2026
ACL Papers & TrustNLP
Co-organized TrustNLP @ ACL'26. ACL papers: LLM Unlearning, SWAN, ARES, and AutoSUIT Bench.
Jul 6-11, 2026
ICML
🏆 Two papers: Misaligned Agents and Prompt Injection (spotlight).
2026
India AI Summit
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.
2026
Amazon Science
Amazon Science article featuring my team's work: Building trust into AI.
2026
Catastrophic Risk Evaluation
Amazon Science blog: How catastrophic is your LLM?
2026
Open Collaboration
Red Hat blog: AI trust through open collaboration: A new chapter for responsible innovation.
2026
Trusted AI Symposium
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.
2026
ICLR
Collaborated on three papers: LLM Deception, Catastrophic Risk, and Jailbreak Generalization.

2025

2025
🏆 Agent X Competition
Winner of the AgentX Benchmark & Evaluation Track for Establishing Best Practices for Building Rigorous Agentic Benchmarks.
2025
SemEval Unlearning Challenge
Co-organized the SemEval Unlearning Challenge at ACL.
2025
Nova AI Challenge
My team leads the Nova AI Challenge, supporting 10 universities annually on safety research.
2025
AI Governance Forums
Represented Amazon at the Frontier Model Forum and Partnership on AI.
2025
NeurIPS
Papers: VMDT, Agentic Benchmarks, and LLM Unlearning (workshop).
2025
NAACL
Paper: Localizing and Deleting Toxic Memories in LLMs (Findings).
2025
ICLR
Paper: Quantitative Certification of Bias in LLMs.
2025
AAAI Workshops
Papers: MUNCH and K-Edit (Preventing and Detecting LLM Misinformation workshop).

2024

2024
EMNLP
Papers: FLIRT, Attribute Controlled Fine-tuning, Data Advisor, and Self-contradictory Reasoning (Findings).
2024
ACL
Paper: Tree-of-Traversals.
2024
NAACL
Papers: Slang in LLMs, LLM Steerability, Pronoun Tokenization Parity (Findings), MICo (Findings), BELIEVE (TrustNLP workshop), and Debiasing Image Captioning (TrustNLP workshop).
2024
NeurIPS Workshop
Paper: LLM-PIEval (AdvML Frontiers workshop).
2024
ICASSP Workshop
Paper: Partial Federated Learning (Trustworthy Speech Processing workshop).

2023

2023
AI For Open Society @ KDD
Invited panelist.
2023
EMNLP
Papers: Controlled Generation Evaluation, Faithful Model Evaluation, INVITE (Findings), and Coordinated Replay for Continual FL (Industry Track).
2023
ACL
Paper: Resolving Ambiguities in Text-to-Image.
2023
NeurIPS Workshop
Paper: JAB (Socially Responsible LM Research workshop).
2023
KDD
Paper: FedMultimodal.
2023
ACM FAccT
Paper: Centering Trans & Non-Binary Voices.
2023
ICASSP
Papers: Self-healing via Error Detection and Catastrophic Forgetting in Continual FL.
2023
ICDM Industry Day
Papers: Fairness in Large Scale NLU and Privacy in the Time of LMs.
2023
Interspeech
Paper: Sampling Bias in NLU Models.
2023
IEEE SLT
Paper: Decoding Algorithms and Fairness.
2023
CIKM Workshop
Paper: LLM Steerability toward Personas (Personalized Generative AI workshop).

2022

2022
FL4NLP @ ACL
Invited speaker.
2022
ACL
Papers: Canary Extraction in NLU, Fairness via Prediction Sensitivity, Intrinsic & Extrinsic Fairness Metrics, Multi-VALUE, Gender Bias via Counterfactual Role Reversal (Findings), and DP Decoding in LLMs (TrustNLP workshop).
2022
NAACL
Papers: FL with Noisy User Feedback, Mixed-Domain Translation via FL, FedNLP (Findings), and Controlled Data Generation for NLU (Industry Track).
2022
AACL
Paper: Chasing the Tail with Domain Generalization.
2022
ICASSP
Papers: Advin, Learnings from FL in the Real World, and Efficient DP-SGD for NLU.
2022
EMNLP Industry Track
Paper: Model Interpretation for Conversational Assistants.

2020 and Older

2016
USC
🏆 Best PhD Thesis Pitch Award.
2016
IEEE Signal Processing Society
🏆 Travel award to ICASSP 2016.
2015
Interspeech Paralinguistics Challenge
🏆 Winner, Degree of Nativeness Sub-Challenge, for Automated Evaluation of Non-native English Pronunciation Quality.
2015
Phi Beta Kappa Alumni in Southern California
Graduate Study Award scholarship recipient.
2013
Interspeech Paralinguistics Challenge
🏆 Winner, Social Signals Sub-Challenge, for Paralinguistic Event Detection from Speech.
2010-2014
USC
Provost Fellowship.
2009
Info-USA Exchange Scholarship
Scholarship recipient.