Virtue AI Research | Pioneering AI Innovations

Virtue AI
RESEARCH TERMS

We conduct pioneering AI research to empower and ensure safe and secure AI.

Red Teaming & Risk Assessments

Pioneering comprehensive AI risk assessment across multiple sectors and languages. Our advanced red teaming algorithms rigorously test AI models and systems, ensuring robust safety measures aligned with global regulations.

Guardrail & Threat Mitigation

Developing cutting-edge, customizable content moderation solutions for text, image, audio, and video. Our guardrails offer transparent, policy-compliant protection with unparalleled speed and efficiency.

Safe Models & Agents

Crafting AI models and agents with inherent safety features, from secure code generation to safe decision-making. We’re integrating safety and compliance directly into AI development processes, setting new standards for responsible AI.

Publications

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.

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding.

Differentially Private Synthetic Data via Foundation Model APIs 2: Text.

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing.

Virtue AI
RESEARCH TERMS

Red Teaming & Risk Assessments

Guardrail & Threat Mitigation

Safe Models & Agents

Publications

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.

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding.

Differentially Private Synthetic Data via Foundation Model APIs 2: Text.

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing.

Empower. Ensure.

Safe & Secure AI

Virtue AI RESEARCH TERMS

Red Teaming & Risk Assessments

Guardrail & Threat Mitigation

Safe Models & Agents

Publications

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.

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding.

Differentially Private Synthetic Data via Foundation Model APIs 2: Text.

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing.

Empower. Ensure.

Safe & Secure AI

Virtue AI
RESEARCH TERMS