Research

Research Insights

From academic research to production-grade AI safety.

DP-OPT: Make Large Language Model Your Differentially-Private Prompt Engineer

Effective and Efficient Federated Tree Learning on Hybrid Data

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits

MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles.

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

Fair Federated Learning via the Proportional Veto Core

SHINE: Shielding Backdoors in Deep Reinforcement Learning.