الباحثون

Zhonghai Wu

المنشورات 2

نسخة أولية وصول مفتوح

ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems

Weilin Jin, Mingyu Wang, Taiyu Zhu وآخرون · 2026

In LLM-based agent systems, failures can originate from early steps whose effects propagate through subsequent interactions, making their origins difficult to identify. To trace such failures back to their origin, failure attribution has been formulated as the task of identifying the earliest step responsible for the f …

نسخة أولية وصول مفتوح

zkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models

Junkai Liang, Zhanpeng Guo, Pengfei Wu وآخرون · 2026

Auditing the claimed outcomes of large language model (LLM) training is challenging when model weights and training data are private, while cryptographically proving the full training process is prohibitively expensive at Transformer scale. We present zkLLMPoT, a zero-knowledge framework that certifies auditor-defined …

المؤلفون المشاركون