Fan Zhang

The paper introduces a comprehensive security framework, AgentRFC, to systematically analyze and test the security conformance of various AI agent protocols, identifying critical design gaps, especially in protocol composition.

The paper analyzes transaction fee mechanisms in modern blockchains that use parallel execution and contingency, proving an inherent trade-off between minimizing risks for users and maximizing revenue for schedulers.

The paper introduces PostRI, a novel method that allows for computing a Randomization Interval (RI) for differentially private median queries after the median has already been estimated, significantly improving utility compared to prior work.

The paper introduces Appraisal, a novel Screening-then-Linkage framework (PPRS) that significantly improves the scalability and efficiency of Privacy-Preserving Record Linkage by incorporating a lightweight screening phase.

This paper introduces MCTS-Guided Group Relative Policy Optimization (M-GRPO) to enhance LLM spatial reasoning by improving the decomposition of complex tasks into optimal sub-tasks.

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multimodal models.

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at visual grounding, they struggle with fine-grained semantic following.

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals for open-ended reasoning tasks.

MOSAIC is a novel scheduling framework that significantly accelerates Mixture-of-Agents (MoA) workloads by jointly optimizing expert placement and utilizing confidence-aware adaptive aggregation.