Chaochao Lu
- Papers
- 17
Cite
Notes
Only stored in your browser.
Authored papers
17AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
arXiv 2026
MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
arXiv 2026
CauScale: Neural Causal Discovery at Scale
arXiv 2026
Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference
arXiv 2026
Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
arXiv 2025
LINA: Learning INterventions Adaptively for Physical Alignment and Generalization in Diffusion Models
arXiv 2025
The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
arXiv 2025
RePO: Replay-Enhanced Policy Optimization
arXiv 2025
CauSight: Learning to Supersense for Visual Causal Discovery
arXiv 2025
VLMs Can Aggregate Scattered Training Patches
arXiv 2025
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
arXiv 2025
DEPO: Dual-Efficiency Preference Optimization for LLM Agents
arXiv 2025
OASIS: Open Agent Social Interaction Simulations with One Million Agents
arXiv 2024
Causal Evaluation of Language Models
arXiv 2024
Interpreting Low-level Vision Models with Causal Effect Maps
arXiv 2024
From Imitation to Introspection: Probing Self-Consciousness in Language Models
arXiv 2024
CLEAR: Can Language Models Really Understand Causal Graphs?
arXiv 2024
Affiliations
Frequent co-authors
10from 17 papers