PPaperPicks

Xinghua Qu

11 papers at tracked venues · 11 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation
  2. Confound from all Sides, Distill with Resilience: Multi-Objective Adversarial Paths to Zero-Shot Robustness
  3. Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices
  4. LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation
  5. Machine Unlearning via Task Simplex Arithmetic
  6. Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
  7. Robustifying Zero-Shot Vision Language Models by Subspaces Alignment
  8. Stabilizing Modality Gap & Lowering Gradient Norms Improve Zero-Shot Adversarial Robustness of VLMs
  9. You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs
  10. Adaptive In-Context Learning with Large Language Models for Bundle Generation
  11. Large Language Models for Intent-Driven Session Recommendations