PPaperPicks

Jin Song Dong

14 papers at tracked venues · 14 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. ARuleCon: Agentic Security Rule Conversion
  2. CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels
  3. Failures to Surface Harmful Contents in Video Large Language Models
  4. Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation
  5. Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications
  6. LLMQuA: Practical Backdoor Injection on Large Language Model Quantization
  7. ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models
  8. Clustering Properties of Self-Supervised Learning
  9. Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision
  10. F3Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos
  11. FracFace: Breaking the Visual Clues - Fractal-Based Privacy-Preserving Face Recognition
  12. Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods
  13. RvLLM: LLM Runtime Verification with Domain Knowledge
  14. A Symbolic Rule Integration Framework with Logic Transformer for Inductive Relation Prediction