pith. sign in

Dongrui Liu

Identifiers

  • name variant Dongrui Liu 0.60 · backfill

Papers (22)

  1. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security cs.AI · 2026 · author #1
  2. Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents cs.AI · 2026 · author #5
  3. Preference-aware Influence-function-based Data Selection Method for Efficient Fine-Tuning cs.LG · 2026 · author #3
  4. Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs cs.CR · 2026 · author #8
  5. A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook cs.SD · 2026 · author #12
  6. Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion cs.CV · 2026 · author #10
  7. Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models cs.AI · 2026 · author #7
  8. Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models cs.CV · 2026 · author #2
  9. What Do EEG Foundation Models Capture from Human Brain Signals? cs.AI · 2026 · author #9
  10. Attributing Emergence in Million-Agent Systems cs.AI · 2026 · author #9
  11. TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems cs.CL · 2026 · author #6
  12. AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems cs.LG · 2026 · author #5
  13. Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking cs.AI · 2026 · author #7
  14. On the Blessing of Pre-training in Weak-to-Strong Generalization cs.LG · 2026 · author #5
  15. Multilingual Safety Alignment via Self-Distillation cs.LG · 2026 · author #3
  16. Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex cs.AI · 2026 · author #9
  17. Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability cs.AI · 2026 · author #11
  18. ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis cs.AI · 2026 · author #13
  19. SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond cs.LG · 2026 · author #8
  20. AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security cs.AI · 2026 · author #1
  21. A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence cs.AI · 2025 · author #19
  22. Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring cs.CL · 2025 · author #6

Mentions

  • 2605.29801 #1 · arxiv_oai · confidence 0.70 Dongrui Liu
  • 2605.28201 #5 · arxiv_oai · confidence 0.70 Dongrui Liu
  • 2502.05242 #6 · arxiv_oai · confidence 0.70 Dongrui Liu
  • 2605.21541 #8 · arxiv_oai · confidence 0.70 Dongrui Liu
  • 2605.21422 #3 · arxiv_oai · confidence 0.70 Dongrui Liu
  • 2605.20266 #12 · arxiv_oai · confidence 0.70 Dongrui Liu
  • 2605.18346 #10 · arxiv_oai · confidence 0.70 Dongrui Liu
  • 2605.17770 #7 · arxiv_oai · confidence 0.70 Dongrui Liu
  • 2605.17310 #2 · arxiv_oai · confidence 0.70 Dongrui Liu

Frequent Coauthors