Jun Luo

Venues

Frequent coauthors

Papers

1. Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models
   AAAI 2026 ·

   Ziwei Liu

   DBLP profile ↗ORCID search ↗
2. Cheating Stereo Matching in Full-Scale: Physical Adversarial Attack Against Binocular Depth Estimation in Autonomous Driving
   AAAI 2026 ·

   Kangqiao Zhao

   DBLP profile ↗ORCID search ↗
3. To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending
   ACL 2026 ·

   Jin Gan

   DBLP profile ↗ORCID search ↗
4. Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position
   AAAI 2026 ·

   Zhixin Xie

   DBLP profile ↗ORCID search ↗
5. Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
   NeurIPS 2025 ·

   Zhixin Xie

   DBLP profile ↗ORCID search ↗
6. Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
   NeurIPS 2025 ·

   Jingjing Jiang

   DBLP profile ↗ORCID search ↗
7. Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning
   ICCV 2025 ·

   Jingjing Jiang

   DBLP profile ↗ORCID search ↗
8. Dagger Behind Smile: Fool LLMs with a Happy Ending Story
   EMNLP 2025 ·

   Xurui Song

   DBLP profile ↗ORCID search ↗
9. Do Not DeepFake Me: Privacy-Preserving Neural 3D Head Reconstruction Without Sensitive Images
   AAAI 2025 ·

   Jiayi Kong

   DBLP profile ↗ORCID search ↗
10. Fairness in Streaming Submodular Maximization Subject to a Knapsack Constraint
    SIGKDD 2024 ·

    Shuang Cui

    DBLP profile ↗ORCID search ↗