← authors · overview

• GuardReasoner: Towards Reasoning-based LLM Safeguards
  2025 · 2 citations
• V3DB: Audit-on-Demand Zero-Knowledge Proofs for Verifiable Vector Search over Committed Snapshots
  2026
• ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
  2025
• The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation
  2025
• GuardReasoner: Towards Reasoning-based LLM Safeguards
  2025
• Efficient Inference for Large Reasoning Models: A Survey
  2025
• Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads
  2025
• Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
  2025
• Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
  2025
• FlipAttack: Jailbreak LLMs via Flipping
  2024