PPaperPicks

Fenghua Weng

3 papers at tracked venues · 2 at CORE A* · active 2025–2025

DBLP profile ↗ORCID search ↗

Venues

AAAI ×1ACL ×1EMNLP ×1

Frequent coauthors

Yi Wang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training
    EMNLP 2025 · Fenghua Weng
  2. DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing
    ACL 2025 ·
    Yi Wang
    DBLP profile ↗ORCID search ↗
  3. MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models
    AAAI 2025 · Fenghua Weng