Profiles2024-2026
Chaozhuo Li
Beijing University of Posts and Telecommunications
14Papers
1Last author
18Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers14
- From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in LRMs via Decoupled Reasoning and ControlAuthor 3 of 5ACL 2026 · 5 citations
- Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations ReasoningAuthor 2 of 6ACL 2026 · 1 citation
- Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning ProtocolsAuthor 2 of 6KDD 2026
- Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion PredictionAuthor 2 of 4CVPR 2026
- MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror CraftingAuthor 2 of 6AAAI 2026
- Paradigm Shift of GNN Explainer from Label Space to Prototypical Representation SpaceAuthor 7 of 9ICLR 2026
- MRR-FV: Unlocking Complex Fact Verification with Multi-Hop Retrieval and ReasoningAuthor 2 of 7AAAI 2025 · 6 citations
- Beyond Text: Fine-Grained Multi-Modal Fact Verification with Hypergraph TransformersAuthor 2 of 5AAAI 2025 · 4 citations
- What Is a Good Question? Assessing Question Quality via Meta-Fact CheckingAuthor 3 of 9AAAI 2025 · 3 citations
- Ghidorah: Towards Robust Multi-Scale Information Diffusion Prediction via Test-Time TrainingAuthor 2 of 5AAAI 2025 · 2 citations
- LlmFixer: Fix the Helpfulness of Defensive Large Language ModelsAuthor 5 of 5EMNLP Findings 2025
- Evidence Retrieval is almost All You Need for Fact VerificationAuthor 2 of 6ACL Findings 2024 · 11 citations
- Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement LearningAuthor 2 of 4NeurIPS 2024 · 8 citations
- BaitAttack: Alleviating Intention Shift in Jailbreak Attacks via Adaptive Bait CraftingAuthor 2 of 6EMNLP 2024
