Jiahao Yu

GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization

Decoupled Alignment for Robust Plug-and-Play Adaptation

GPO: Learning from Critical Steps to Improve LLM Reasoning

The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)

BlockScan: Detecting Anomalies in Blockchain Transactions

BlockFound: Customized blockchain foundation model for anomaly detection

BOOST: Enhanced Jailbreak of Large Language Model via Slient eos Tokens

PFT: Enhancing Prompt Injection Robustness via Position-Enhanced Finetuning

Decoupled Alignment for Robust Plug-and-Play Adaptation