William Yang Wang
25 papers · 1433 citations
Most-cited papers
- Shadow Alignment: The Ease Of Subverting Safely-aligned Language Models2023 · 282 citations
- Automatically Correcting Large Language Models: Surveying The Landscape Of Diverse Self-correction Strategies2023 · 281 citations
- Guiding Instruction-based Image Editing Via Multimodal Large Language Models2023 · 172 citations
- Weak-to-strong Jailbreaking On Large Language Models2024 · 109 citations
- ULN: Towards Underspecified Vision-and-language Navigation2022 · 2 citations
- G\"odel Agent: A Self-referential Agent Framework For Recursive Self-improvement2024 · 2 citations
- Termigen: High-fidelity Environment And Robust Trajectory Synthesis For Terminal Agents2026
- Proactive Agent Research Environment: Simulating Active Users To Evaluate Proactive Assistants2026
- Devops-gym: Benchmarking AI Agents In Software Devops Cycle2026
Topics