Hao Hu

The paper introduces Sol2Vy, a framework that enables cross-language knowledge transfer from Solidity to Vyper, allowing effective vulnerability detection in low-resource smart contracts without needing labeled Vyper training data.

This paper provides the first comprehensive, end-to-end survey dedicated to the security of Retrieval-Augmented Generation (RAG) systems, systematically mapping threats, defenses, and benchmarks across the entire pipeline.

The paper introduces FoodGuardBench, a comprehensive benchmark and a specialized guardrail model (FoodGuard-4B) to rigorously test and mitigate the severe food safety risks posed by large language models.

The paper introduces MORPH, a framework that reformulates Zero-Knowledge Proof (ZKP) computations to efficiently utilize AI ASICs like TPUs, achieving up to 10x higher throughput on NTT.

VIPER-MCP is a novel, end-to-end automated framework that detects and dynamically confirms the exploitability of taint-style vulnerabilities in Model Context Protocol (MCP) servers, achieving high-fidelity vulnerability discovery in real-world systems.

SAMark introduces a self-anchored text watermarking framework that achieves high robustness (up to 90.2% TP@FP1%) against challenging paragraph-level paraphrasing attacks by establishing a step-independent green region in semantic space.

EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.

This paper introduces the Data-Model Compatibility (DMC) metric to quantify how suitable a dataset is for reasoning distillation, showing that optimizing data selection using DMC significantly improves the performance of smaller student models.

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate failure diagnosis and generalizing learned lessons.

The paper introduces GTA, a scalable framework for generating realistic, multi-hop web-agent tasks with dense, executable trajectories, addressing the current lack of process-level supervision in web agent research.

This paper refines word-based grammatical error annotation for L2 Korean by adapting existing resources to better reflect Korean morphology and error types, improving the evaluation of Korean Grammatical Error Correction (K-GEC) systems.

COMPASS introduces a Cognitive MCTS-Guided Process Alignment framework to ensure robust safety for LLM search agents by identifying and supervising risky intermediate steps in multi-step reasoning.