4 papers
Employing the Structural Power to Achieve Supply-Demand Balanced Payment Channel Networks
Shuyao Xiao, Shengling Wang, Hongwei Shi +2
Blockchain technology faces scalability challenges because transactions must be validated and recorded across the network. Payment channel networks (PCNs) improve efficiency by mov…
Who Drives the Probability Game of VLMs? A Temporal Causal Drive Evaluation Framework
Shuyao Xiao, Shengling Wang, Haoyu Niu +4
Vision-language models (VLMs) are increasingly evaluated on complex image and video understanding tasks, yet conventional metrics primarily assess final-answer quality and reveal l…
When Errors Become Memories: Causal Pathway Tracing in Multi-Turn Memory-Augmented LLMs
Shuyao Xiao, Shengling Wang, Xuan Chen +8
Long-term memory enables large language models (LLMs) to preserve and reuse information across interactions, but it can also turn localized errors into persistent risks. Existing w…
SubZero+: Efficient Zeroth-Order LLM Fine-Tuning via Large Learning Rates
Ziming Yu, Shuyao Xiao, Xingyu Zhao +6
Zeroth-order (ZO) optimization enables backpropagation-free fine-tuning of large language models, but existing ZO methods suffer from high-variance gradient estimators, making conv…