pith. sign in

Haibo Jin

Identifiers

  • name variant Haibo Jin 0.60 · backfill

Papers (11)

  1. Closing the Loop on Latent Reasoning via Test-Time Reconstruction cs.AI · 2026 · author #2
  2. SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization cs.LG · 2026 · author #2
  3. TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization cs.CL · 2026 · author #5
  4. Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation cs.AI · 2026 · author #3
  5. Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems cs.AI · 2026 · author #3
  6. Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems cs.MA · 2026 · author #1
  7. Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting cs.CL · 2026 · author #3
  8. Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain cs.CL · 2025 · author #2
  9. GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs cs.CL · 2025 · author #1
  10. Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems cs.AI · 2025 · author #15
  11. Deep Person Re-Identification with Improved Embedding and Efficient Training cs.CV · 2017 · author #1

Mentions

  • 2606.06252 #2 · arxiv_oai · confidence 0.70 Haibo Jin
  • 2602.03695 #1 · arxiv_oai · confidence 0.70 Haibo Jin
  • 2605.21948 #2 · arxiv_oai · confidence 0.70 Haibo Jin
  • 2605.21318 #5 · arxiv_oai · confidence 0.70 Haibo Jin
  • 2504.01990 #15 · arxiv_oai · confidence 0.70 Haibo Jin

Frequent Coauthors