Scholar
Chengcan Wu
Google Scholar ID: E2ij2ugAAAAJ
Peking University
Language model safety alignment
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
7
H-index
2
i10-index
0
Publications
3
Co-authors
0
Contact
No contact links provided.
Publications
9 items
Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents
2026
Cited
0
SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents
2026
Cited
0
Absorber LLM: Harnessing Causal Synchronization for Test-Time Training
2026
Cited
0
ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
2026
Cited
0
RACA: Representation-Aware Coverage Criteria for LLM Safety Testing
2026
Cited
0
Monitoring LLM-based Multi-Agent Systems Against Corruptions via Node Evaluation
2025
Cited
0
Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
2025
Cited
0
ReGA: Representation-Guided Abstraction for Model-based Safeguarding of LLMs
2025
Cited
0
Load more
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
