6 citations · 36 across the 27 of their papers we have counts for
29 papers
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
Yixuan Wang, Yifei Chen, Haichao Zhang +6
Reinforcement learning (RL) with group-relative advantages has become the de facto standard for post-training language model reasoners. However, when optimizing multiple reward obj…
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu +11
Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memo…
Compute Allocation for Self-Evolving LLMs: From Depth-Breadth to Multi-Armed Bandits
Sixue Xing, Haoyu He, Kerui Wu +4
LLM-guided evolutionary search (Evolve systems) has reached state-of-the-art results on mathematical and combinatorial tasks, yet most existing systems report only the best of many…
Attention Sinks and Outliers in Attention Residuals
Haozheng Luo, Haoran Dai, Shaoyang Zhang +10
We propose OASIS, an outlier- and sink-aware method that stabilizes dual-normalized attention-residual architectures through explicit null routing and token-to-depth null coupling.…
Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning
Eric Hanchen Jiang, Levina Li, Rui Sun +9
Large Language Models (LLMs) have shown remarkable performance in completing various tasks. However, solving complex problems often requires the coordination of multiple agents, ra…
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
Haozheng Luo, Yimin Wang, Jiahao Yu +2
We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike p…
FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning
Haozheng Luo, Zhuolin Jiang, Md Zahid Hasan +2
We propose FROST, an attention-aware method for efficient reasoning. Unlike traditional approaches, FROST leverages attention weights to prune uncritical reasoning paths, yielding…
AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning
Zhenyu Pan, Yiting Zhang, Zhuo Liu +13
LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to jailbreak, prompt-injection, and…
Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety
Zhenyu Pan, Yiting Zhang, Yutong Zhang +8
Multi-agent systems (MAS) built on multimodal large language models exhibit strong collaboration and performance. However, their growing openness and interaction complexity pose se…
RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility
Haoyu He, Haozheng Luo, Yan Chen +1
Predicting human mobility is inherently challenging due to complex long-range dependencies and multi-scale periodic behaviors. To address this, we introduce RHYTHM (Reasoning with…
Efficient Temporal Tokenization for Mobility Prediction with Large Language Models
Haoyu He, Haozheng Luo, Yan Chen +1
We introduce RHYTHM (Reasoning with Hierarchical Temporal Tokenization for Human Mobility), a framework that leverages large language models (LLMs) as spatio-temporal predictors an…
FairReason: Balancing Reasoning and Social Bias in MLLMs
Zhenyu Pan, Yutong Zhang, Jianshu Zhang +6
Multimodal Large Language Models (MLLMs) already achieve state-of-the-art results across a wide range of tasks and modalities. To push their reasoning ability further, recent studi…
POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models
Yangguang Shao, Xinjie Lin, Haozheng Luo +4
Large language models (LLMs) have achieved remarkable success in various domains, primarily due to their strong capabilities in reasoning and generating human-like text. Despite th…
Fast and Low-Cost Genomic Foundation Models via Outlier Removal
Haozheng Luo, Chenghao Qiu, Maojiang Su +5
To address the challenge of scarce computational resources in genomic modeling, we introduce GERM, a genomic foundation model with strong compression performance and fast adaptabil…
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models
Haozheng Luo, Chenghao Qiu, Yimin Wang +9
We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first compre…
ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction
Haoyu He, Haozheng Luo, Qi R. Wang
Predicting human mobility across multiple cities presents significant challenges due to the complex and diverse spatial-temporal dynamics inherent in different urban environments.…
Decoupled Alignment for Robust Plug-and-Play Adaptation
Haozheng Luo, Jiahao Yu, Wenxin Zhang +9
We introduce a training-free safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning or reinforcement learning from human fe…
Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action
Zhenyu Pan, Haozheng Luo, Manling Li +1
We present a Conversational Chain-of-Action (Conv-CoA) framework for Open-domain Conversational Question Answering (OCQA). Compared with literature, Conv-CoA addresses three major…
Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries
Jiahao Yu, Haozheng Luo, Jerry Yao-Chieh Hu +3
Recent advances in Large Language Models (LLMs) have led to impressive alignment where models learn to distinguish harmful from harmless queries through supervised finetuning (SFT)…
Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
Jerry Yao-Chieh Hu, Pei-Hsuan Chang, Robin Luo +4
We introduce an Outlier-Efficient Modern Hopfield Model (termed ) and use it to address the outlier inefficiency problem of {training} gigantic transformer-base…
Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
Zhenyu Pan, Haozheng Luo, Manling Li +1
We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA). Compared to the literature, CoA overcomes two major challenges of curre…
SMUTF: Schema Matching Using Generative Tags and Hybrid Features
Yu Zhang, Mei Di, Haozheng Luo +2
We introduce SMUTF (Schema Matching Using Generative Tags and Hybrid Features), a unique approach for large-scale tabular data schema matching (SM), which assumes that supervised l…
SciAnnotate: A Tool for Integrating Weak Labeling Sources for Sequence Labeling
Mengyang Liu, Haozheng Luo, Leonard Thong +3
Weak labeling is a popular weak supervision strategy for Named Entity Recognition (NER) tasks, with the goal of reducing the necessity for hand-crafted annotations. Although there…
MBGDT:Robust Mini-Batch Gradient Descent
Hanming Wang, Haozheng Luo, Yue Wang
In high dimensions, most machine learning method perform fragile even there are a little outliers. To address this, we hope to introduce a new method with the base learner, such as…