Haozheng Luo

PhD student@Northwestern University, Northwestern University·美国·OpenReview

研究方向

Parameter Efficiency Fine-Tuning · Genomic Foundation Model · Human Mobility · Memory Retrieval · Jailbreak · Chain-of-thought · Attention Outlier · Test Time Scaling Law · Efficient AI · Foundation Model · Trustworthy AI · NLP · Machine Learning · LightGBM

Haozheng Luo

FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning

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

Learning to Rank Chain-of-Thought: Using a Small Model

Decoupled Alignment for Robust Plug-and-Play Adaptation

AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

Conv-CoA: Open-domain Question Answering via Conversational Chain-of-Action with Hopfield Retriever

Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models

Fast and Low-Cost Genomic Foundation Models via Outlier Removal

RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility

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

SPARQ: Outlier-free SpeechLM with Fast Adaptation and Robust Quantization

Decoupled Alignment for Robust Plug-and-Play Adaptation

SWGA: A Distributed Hyperparameter Search Method for Time Series Prediction Models