221 citations · 708 across the 59 of their papers we have counts for
63 papers
Collective Bias Mitigation via Model Routing and Collaboration
Mingzhe Du, Luu Anh Tuan, Xiaobao Wu +7
Large language models (LLMs) are increasingly deployed in public health, finance, and governance, requiring both accuracy and societal value alignment. Despite recent advances, LLM…
Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs
Vu Duc Anh, Nhat M. Hoang, Do Xuan Long +3
Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LLMs). In this work, we propose…
MatReplace: A Reference-Free, Conditioning-Aligned Benchmark for Material Replacement in Interior Scenes
Mingzhe Du, Thong Thanh Nguyen, Nguyen Tran Cong Duy +2
Material replacement is a common interior-design operation: changing the material of a selected surface while preserving its geometry, surroundings, and illumination. Despite its c…
TIGER: Text-Conditioned Visual Gated Routing with Acceptance Alignment for Multimodal Speculative Decoding
Quynh Vo, Cong-Duy Nguyen, Ponhvoan Srey +2
Speculative decoding accelerates autoregressive generation by letting a lightweight drafter propose multiple tokens that are verified by a larger target model. Although effective f…
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Mingzhe Du, Luu Anh Tuan, Tianyi Wu +4
Repository-level vulnerability reproduction is a demanding software engineering (SE) task: an agent must inspect a codebase, infer the input grammar that reaches a vulnerable path,…
Paper Espresso: From Paper Overload to Research Insight
Mingzhe Du, Luu Anh Tuan, Dong Huang +1
The accelerating pace of scientific publishing makes it increasingly difficult for researchers to stay current. We present Paper Espresso, an open-source platform that automaticall…
ONOTE: Hypergraph-Grounded Omnimodal Reasoning for Computational Music Science
Menghe Ma, Siqing Wei, Yuecheng Xing +7
Omnimodal notation processing, centered on sheet music, is a controlled scientific setting in which auditory, visual, symbolic, and physical representations must encode the same mu…
BenchBench: Benchmarking Automated Benchmark Generation
Yandan Zheng, Haoran Luo, Zhenghong Lin +2
Benchmarks are the de facto standard for tracking progress in large language models (LLMs), yet static test sets can rapidly saturate, become vulnerable to contamination, and are c…
Contextual Representation Flow Across Depth in State-Space and Transformer Architectures
Nhat M. Hoang, Do Xuan Long, Cong-Duy Nguyen +3
State Space Models (SSMs) have emerged as efficient, linear-time alternatives to Transformer-Based Models (TBMs) for long-context processing. However, their different mechanisms ra…
Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
Haoran Luo, Haihong E, Guanting Chen +8
Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. Graph…
MUR: Momentum Uncertainty guided Reasoning for Large Language Models
Hang Yan, Fangzhi Xu, Rongman Xu +8
Large Language Models have achieved impressive performance on reasoning-intensive tasks, yet optimizing their reasoning efficiency remains an open challenge. While Test-Time Scalin…
Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines
Do Xuan Long, Duong Ngoc Yen, Do Xuan Trong +5
In-context learning (ICL) is an important yet not fully understood ability of pre-trained large language models (LLMs). It can greatly enhance task performance using a few examples…
Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers
Viet-Anh Nguyen, Shiqian Zhao, Gia Dao +3
Recently, Large Reasoning Models (LRMs) have demonstrated superior logical capabilities compared to traditional Large Language Models (LLMs), gaining significant attention. Despite…
EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
Yuhao Qing, Boyu Zhu, Mingzhe Du +9
Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To addre…
Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding
Thong Nguyen, Zhiyuan Hu, Xu Lin +3
Recent years have witnessed outstanding advances of large vision-language models (LVLMs). In order to tackle video understanding, most of them depend upon their implicit temporal u…
When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
Shiqian Zhao, Jiayang Liu, Yiming Li +9
Modern text-to-image (T2I) generation systems (e.g., DALLE 3) exploit the memory mechanism, which captures key information in multi-turn interactions for faithful generation…
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Kun Wang, Guibin Zhang, Zhenhong Zhou +100
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communi…
HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation
Haoran Luo, Haihong E, Guanting Chen +9
Standard Retrieval-Augmented Generation (RAG) relies on chunk-based retrieval, whereas GraphRAG advances this approach by graph-based knowledge representation. However, existing gr…
KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
Haoran Luo, Haihong E, Yikai Guo +7
Knowledge Base Question Answering (KBQA) aims to answer natural language questions with a large-scale structured knowledge base (KB). Despite advancements with large language model…
MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering
Zhang Siyue, Xue Yuxiang, Zhang Yiming +3
Understanding temporal relations and answering time-sensitive questions is crucial yet a challenging task for question-answering systems powered by large language models (LLMs). Ex…
Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths
Yew Ken Chia, Guizhen Chen, Weiwen Xu +3
Advanced models such as OpenAI o1 exhibit impressive problem-solving capabilities through step-by-step reasoning. However, they may still falter on more complex problems, making er…
A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications
Wenyi Xiao, Zechuan Wang, Leilei Gan +9
With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical. Direct Preference Optimization (DPO) has…
Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
Shuai Zhao, Xiaobao Wu, Cong-Duy Nguyen +4
Parameter-efficient fine-tuning (PEFT) can bridge the gap between large language models (LLMs) and downstream tasks. However, PEFT has been proven vulnerable to malicious attacks.…
Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs
Shuai Zhao, Leilei Gan, Zhongliang Guo +5
Despite being widely applied due to their exceptional capabilities, Large Language Models (LLMs) have been proven to be vulnerable to backdoor attacks. These attacks introduce targ…