Dongrui Liu

Dongrui Liu on Hugging Face Daily Papers: 12 papers, 4 in the top 3 of their day, 545 upvotes.

1. Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5 28 upvotes, #4 of 2026-02-20
2. A Trajectory-Based Safety Audit of Clawdbot (OpenClaw) 22 upvotes, #5 of 2026-02-18
3. DeepSight: An All-in-One LM Safety Toolkit 13 upvotes, #18 of 2026-02-13
4. InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery 68 upvotes, #7 of 2026-02-10
5. AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security 121 upvotes, #1 of 2026-01-28
6. LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions 22 upvotes, #18 of 2025-10-10
7. Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents 16 upvotes, #9 of 2025-10-06
8. ExGRPO: Learning to Reason from Experience 72 upvotes, #3 of 2025-10-03
9. A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence 72 upvotes, #2 of 2025-07-29
10. Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report 4 upvotes, #9 of 2025-07-28
11. The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs 56 upvotes, #1 of 2025-07-21
12. RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents 1 upvotes, #48 of 2025-06-05

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.