Justin Wang

5 papers · 2024–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

ACL (2) ICLR (2) NeurIPS (1)

Top co-authors

Andy Zou (3) Dan Hendrycks (3) Maxwell Lin (3) Maksym Andriushchenko (2) Dylan Zhang (2) Derek Duenas (2) Rowan Wang (2) Matt Fredrikson (2) Long Phan (2) Alexandra Souly (1)

Research topics

Artificial Intelligence (3) Machine Learning (3) Core AI (3) Learning Types · Machine Learning (2) Deep Learning (1) Natural Language Processing (1) Learning Types · Deep Learning (1) Optimization & Theory (1) Resources & Methods (1)

Keywords

adversarial attack (2) large language model (2) ai safety (1) instruction tuning (1) model alignment (1) language model (1) synthetic data (1) representation engineering (1) circuit breaker (1) jailbreak attack (1) multimodal language model (1) ai alignment (1) multi-step task (1) llm agent (1) data scarcity (1) agent safety (1) instruction generalization (1) data diversification (1) harmful output (1) unseen semantics (1)

Papers

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents ICLR 2025 Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity ACL 2025 Diversification Catalyzes Language Models’ Instruction Generalization To Unseen Semantics ACL 2025 Tamper-Resistant Safeguards for Open-Weight LLMs ICLR 2025 Improving Alignment and Robustness with Circuit Breakers NeurIPS 2024