AL
Anh Tuan Luu
cs.CLcs.AIcs.LGcs.CVcs.IRcs.CRcs.NEcs.SEcs.CYcs.DB
On Valency
published · living versionsW_zr9mr299·v1 · currentpublished
Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning
with Guizhen Chen, Weiwen Xu, Wotao Yin, Hou Pong Chan
1 version
W_4gdku7ky·v1published
Preprints & journals
132 papers in the corpus · 2014–2026Truth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods2610.23527v1 · Ponhvoan Srey, Jason Lucas, Pittawat Taveekitworachai et al.2026 · 0 citationsarXiv
Reliable Memory from Unstable Growth: Curating Self-Written Agent Playbooks with Randomized Experiments2610.18427v1 · Hoang Pham, Cong-Duy Nguyen, Dong Le et al.2026 · 0 citationsarXiv
Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit2610.18442v1 · Hoang Pham, Duc Anh Vu, Duy Tung Doan et al.2026 · 0 citationsarXiv
Collective Bias Mitigation via Model Routing and Collaboration2610.03240v1 · Mingzhe Du, Luu Anh Tuan, Xiaobao Wu et al.2026 · 0 citationsarXiv
SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents2610.03372v3 · Shangyang Wu, Shuai Zhao, Ziyue Zhu et al.2026 · 0 citationsarXiv
A Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications.42301828 · Xiao, Wenyi, Wang, Zechuan, Gan, Leilei et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(10):13079-13098
Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles2609.22220v1 · Mingzhe Du, Anh Tuan Luu, Dong Huang et al.2026 · 0 citationsarXiv
ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems2608.30441v2 · Shiqian Zhao, Yangfan Zhou, Xinfeng Li et al.2026 · 0 citationsarXiv
MatReplace: A Reference-Free, Conditioning-Aligned Benchmark for Material Replacement in Interior Scenes2608.24107v1 · Mingzhe Du, Thong Thanh Nguyen, Nguyen Tran Cong Duy et al.2026 · 0 citationsarXiv
Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs2608.11573v2 · Vu Duc Anh, Nhat M. Hoang, Do Xuan Long et al.2026 · 0 citationsarXiv
TIGER: Text-Conditioned Visual Gated Routing with Acceptance Alignment for Multimodal Speculative Decoding2607.11131v1 · Quynh Vo, Cong-Duy Nguyen, Ponhvoan Srey et al.2026 · 0 citationsarXiv
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction2607.01764v2 · Mingzhe Du, Luu Anh Tuan, Tianyi Wu et al.2026 · 0 citationsarXiv
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models2606.27679v2 · Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen et al.2026 · 0 citationsarXiv
Don't Read Everything: A Curvature-Conditioned Query for Linear Attention2606.01294v2 · Dong Le, Thong Nguyen, Cong-Duy Nguyen et al.2026 · 0 citationsarXiv
WINDQuant: Weight-Informed Neural Decision-Making for Global Mixed-Precision LLM Quantization2605.26660v2 · Phong Nam Huu Nguyen, Khoi M. Le, Cong-Duy T Nguyen et al.2026 · 0 citationsarXiv
When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift2605.25629v3 · Khoi Le, Tri Cao, Phong Nguyen et al.2026 · 0 citationsarXiv
Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models2605.08974v2 · Tri Cao, Khoi Le, Thong Nguyen et al.2026 · 0 citationsarXiv
Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency2605.06280v5 · Thong Nguyen, Khoi M. Le, Cong-Duy Nguyen et al.2026 · 0 citationsarXiv
ONOTE: Hypergraph-Grounded Omnimodal Reasoning for Computational Music Science2604.20719v2 · Menghe Ma, Siqing Wei, Yuecheng Xing et al.2026 · 0 citationsarXiv
Paper Espresso: From Paper Overload to Research Insight2604.04562v1 · Mingzhe Du, Luu Anh Tuan, Dong Huang et al.2026 · 0 citationsarXiv
Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models2604.00445v2 · Ponhvoan Srey, Quang Minh Nguyen, Xiaobao Wu et al.2026 · 0 citationsarXiv
BenchBench: Benchmarking Automated Benchmark Generation2603.20807v1 · Yandan Zheng, Haoran Luo, Zhenghong Lin et al.2026 · 0 citationsarXiv
OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents2603.03005v1 · Yichao Feng, Haoran Luo, Zhenghong Lin et al.2026 · 0 citationsarXiv
More Bias, Less Bias: BiasPrompting for Enhanced Multiple-Choice Question Answering2511.20086v1 · Duc Anh Vu, Thong Nguyen, Cong-Duy Nguyen et al.2025 · 0 citationsarXiv
MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval2510.09510v2 · Siyue Zhang, Yuan Gao, Xiao Zhou et al.2025 · 0 citationsarXiv
Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs2510.07697v1 · Man Hu, Xinyi Wu, Zuofeng Suo et al.2025 · 0 citationsarXiv
Contextual Representation Flow Across Depth in State-Space and Transformer Architectures2510.06640v3 · Nhat M. Hoang, Do Xuan Long, Cong-Duy Nguyen et al.2025 · 0 citationsarXiv
P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs2510.04503v2 · Shuai Zhao, Xinyi Wu, Shiqian Zhao et al.2025 · 0 citationsarXiv
GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning2509.17437v1 · Guizhen Chen, Weiwen Xu, Hao Zhang et al.2025 · 3 citationsarXiv
Unsupervised Hallucination Detection by Inspecting Reasoning Processes2509.10004v1 · Ponhvoan Srey, Xiaobao Wu, Anh Tuan Luu2025 · 1 citationarXiv
From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning2508.02458v4 · Yichao Feng, Haoran Luo, Lang Feng et al.2025 · 0 citationsarXiv
Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning2507.21892v2 · Haoran Luo, Haihong E, Guanting Chen et al.2025 · 1 citationICML 2026
Affective-ROPTester: Capability and Bias Analysis of LLMs in Predicting Retinopathy of Prematurity2507.05816v1 · Shuai Zhao, Yulin Zhang, Luwei Xiao et al.2025 · 13 citationsarXiv
ClozeMath: Improving Mathematical Reasoning in Language Models by Learning to Fill Equations2506.03763v1 · Quang Hieu Pham, Thuy Duong Nguyen, Tung Pham et al.2025 · 0 citationsarXiv
Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines2506.01265v1 · Do Xuan Long, Duong Ngoc Yen, Do Xuan Trong et al.2025 · 0 citationsarXiv
Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization2505.23387v3 · Mingzhe Du, Luu Anh Tuan, Yue Liu et al.2025 · 0 citationsarXiv
Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers2505.16241v3 · Viet-Anh Nguyen, Shiqian Zhao, Gia Dao et al.2025 · 0 citationsarXiv
SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation2505.14419v1 · Huimin Xu, Xin Mao, Feng-Lin Li et al.2025 · 0 citationsarXiv
Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding2505.12605v1 · Thong Nguyen, Zhiyuan Hu, Xu Lin et al.2025 · 0 citationsarXiv
When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems2504.20376v3 · Shiqian Zhao, Jiayang Liu, Yiming Li et al.2025 · 0 citationsarXiv
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment2504.15585v4 · Kun Wang, Guibin Zhang, Zhenhong Zhou et al.2025 · 1 citationarXiv
Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation2504.13054v1 · Yichao Feng, Shuai Zhao, Yueqiu Li et al.2025 · 0 citationsarXiv
HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation2503.21322v3 · Haoran Luo, Haihong E, Guanting Chen et al.2025 · 10 citationsNeurIPS 2025
Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning2502.14356v1 · Huimin Xu, Xin Mao, Feng-Lin Li et al.2025 · 1 citationarXiv
CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base2502.12591v2 · Cong-Duy Nguyen, Xiaobao Wu, Duc Anh Vu et al.2025 · 0 citationsarXiv
SeaExam and SeaBench: Benchmarking LLMs with Local Multilingual Questions in Southeast Asia2502.06298v1 · Chaoqun Liu, Wenxuan Zhang, Jiahao Ying et al.2025 · 3 citationsarXiv
KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search2501.18922v4 · Haoran Luo, Haihong E, Yikai Guo et al.2025 · 1 citationICML 2025
Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation2501.14166v1 · Cong-Duy Nguyen, Xiaobao Wu, Thong Nguyen et al.2025 · 4 citationsarXiv
MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering2412.15540v2 · Zhang Siyue, Xue Yuxiang, Zhang Yiming et al.2024 · 0 citationsarXiv
AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge2412.13670v2 · Xiaobao Wu, Liangming Pan, Yuxi Xie et al.2024 · 3 citationsarXiv
Career total: 199 works. 132 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.