Profiles2024-2026
Bo Li
University of Chicago
19Papers
13Last author
40Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers19
- BlueCodeAgent: A Blue Teaming Agent Powered by Automated Red Teaming for CodeGen AIAuthor 6 of 6ICML 2026
- UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own ReasoningAuthor 3 of 3ICML 2025 · 1 citation
- GuardAgent: Safeguard LLM Agents via Knowledge-Enabled ReasoningAuthor 12 of 12ICML 2025
- SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation ModelsAuthor 6 of 6ICML 2025
- SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent ExplanationsAuthor 4 of 4ICLR 2025
- ShieldAgent: Shielding Agents via Verifiable Safety Policy ReasoningAuthor 3 of 3ICML 2025
- Sparse Transfer Learning Accelerates and Enhances Certified Robustness: A Comprehensive StudyAuthor 4 of 5AAAI 2025
- AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge BasesAuthor 5 of 5NeurIPS 2024 · 539 citations
- HALC: Object Hallucination Reduction via Adaptive Focal-Contrast DecodingAuthor 5 of 6ICML 2024 · 164 citations
- RigorLLM: Resilient Guardrails for Large Language Models against Undesired ContentAuthor 7 of 7ICML 2024 · 77 citations
- Differentially Private Synthetic Data via Foundation Model APIs 2: TextAuthor 11 of 12ICML 2024 · 71 citations
- DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt EngineerAuthor 5 of 6ICLR 2024 · 70 citations
- LLM-PBE: Assessing Data Privacy in Large Language ModelsAuthor 11 of 12VLDB 2024 · 66 citations
- Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under CompressionAuthor 15 of 15ICML 2024 · 54 citations
- ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous VehiclesAuthor 3 of 3CVPR 2024 · 50 citations
- COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic CircuitsAuthor 4 of 4ICLR 2024 · 12 citations
- ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated LearningAuthor 5 of 6USENIX Security 2024 · 11 citations
- GRATH: Gradual Self-Truthifying for Large Language ModelsAuthor 3 of 3ICML 2024 · 7 citations
- Effective and Efficient Federated Tree Learning on Hybrid DataAuthor 7 of 7ICLR 2024 · 4 citations
