Jie Zhang
- Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity
- DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
- EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
- Large Language Models Miss the Multi-agent Mark
- Mask Image Watermarking
- RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics
- RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models
- Synergistic Tensor and Pipeline Parallelism