KD
Khoa D. Doan
cs.LGcs.CVcs.AIcs.CLcs.CRcs.IRcs.ROstat.MLcs.DCcs.SD
On Valency
published · living versionsW_rjmp4seq·v1 · currentpublished
On the Primacy Bias in RLVR Training
with Phuc Minh Nguyen, Ngoc-Hieu Nguyen, Parshin Shojaee, Chinh Duc La +4
1 version
W_9yx7tx3d·v1published
Preprints & journals
47 papers in the corpus · 2020–2026REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving2609.11209v1 · Tuan Nguyen, Qiran Hu, Banruo Liu et al.2026 · 0 citationsarXiv
Rethinking Molecular Graph Backdoors under Chemistry-aware Admission2606.23361v1 · Thinh T. H. Nguyen, Sze Jue Yang, Khoa D. Doan et al.2026 · 0 citationsarXiv
RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis2606.28385v2 · Minh-Loi Nguyen, Nghiem T. Diep, Hung K. Nguyen et al.2026 · 0 citationsarXiv
Look Before You Zoom: Adaptive Routing for the Resolution-Context Trade-off in Visual RAG2606.21968v1 · Oanh N. Tran, Thanh Quoc Hung Le, Oscar Chew et al.2026 · 0 citationsarXiv
FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation2606.20867v1 · Duc Minh Nguyen, Nghiem Tuong Diep, Binh Gia Nguyen et al.2026 · 0 citationsarXiv
When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning2606.15695v1 · Thinh T. H. Nguyen, Khoa D. Doan, Binh T. Nguyen et al.2026 · 0 citationsarXiv
Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing2606.14084v1 · Duc Minh Nguyen, Bao-Ngoc Dao, Tung M. Luu et al.2026 · 0 citationsarXiv
ViP-VL: Vietnamese Self-supervised Speech Pretraining Model with Vector-Quantization Learning2606.10360v2 · Khanh Le, Kiet Anh Hoang, Bao Nguyen et al.2026 · 0 citationsarXiv
PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers2605.26730v3 · Ngoc Phan Phuoc Loc, Toan Huynh La Viet, Thanh Tran Khanh et al.2026 · 0 citationsarXiv
Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models2605.27101v2 · Oscar Chew, Serhii Honcharenko, Qian-Hui Chen et al.2026 · 0 citationsarXiv
SparseSAM: Structured Sparsification of Activations in Segment Anything Models2605.17633v1 · Hoai-Chau Tran, Chi H. Nguyen, Duy M. H. Nguyen et al.2026 · 0 citationsarXiv
Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road2605.17026v2 · Ngoc-Hieu Nguyen, Parshin Shojaee, Phuc Minh Nguyen et al.2026 · 0 citationsarXiv
DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation2605.16113v1 · Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le et al.2026 · 0 citationsarXiv
PSI-Bench: Interpretable and Clinically Meaningful Evaluation of Depression Patient Simulators2604.25840v2 · Nguyen Khoi Hoang, Shuhaib Mehri, Tse-An Hsu et al.2026 · 0 citationsarXiv
Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family2604.05971v2 · Oscar Chew, Hsiao-Ying Huang, Kunal Jain et al.2026 · 0 citationsarXiv
Decoding the Critique Mechanism in Large Reasoning Models2603.16331v2 · Hoang Phan, Quang H. Nguyen, Hung T. Q. Le et al.2026 · 0 citationsarXiv
The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models2510.02230v1 · Phuc Minh Nguyen, Chinh D. La, Duy M. H. Nguyen et al.2025 · 0 citationsarXiv
Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learning2508.05157v2 · Thinh Nguyen, Le Huy Khiem, Van-Tuan Tran et al.2025 · 0 citationsarXiv
BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning2507.04903v2 · Thinh Dao, Dung Thuy Nguyen, Khoa D Doan et al.2025 · 0 citationsarXiv
LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models2504.10415v2 · Parshin Shojaee, Ngoc-Hieu Nguyen, Kazem Meidani et al.2025 · 1 citationarXiv
Class-Aware Contrastive Optimization for Imbalanced Text Classification2410.22197v1 · Grigorii Khvatskii, Nuno Moniz, Khoa Doan et al.2024 · 3 citationsarXiv
Clean-Label Physical Backdoor Attacks with Data Distillation2407.19203v4 · Thinh Dao, Khoa D Doan, Kok-Seng Wong2024 · 2 citationsarXiv
Flatness-aware Sequential Learning Generates Resilient Backdoors2407.14738v1 · Hoang Pham, The-Anh Ta, Anh Tran et al.2024 · 1 citationarXiv
Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality2407.13803v1 · Duy C. Hoang, Hung T. Q. Le, Rui Chu et al.2024 · 0 citationsarXiv
Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks2407.10825v2 · Quang H. Nguyen, Nguyen Ngoc-Hieu, The-Anh Ta et al.2024 · 1 citationarXiv
MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs2407.10834v3 · Quang H. Nguyen, Thinh Dao, Duy C. Hoang et al.2024 · 2 citationsarXiv
Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generator2407.11078v1 · Thinh Nguyen, Khoa D Doan, Binh T. Nguyen et al.2024 · 1 citationarXiv
Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscape2407.07917v1 · Tuan Nguyen, Dung Thuy Nguyen, Khoa D Doan et al.2024 · 1 citationarXiv
Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated Learning2407.03144v2 · Son Nguyen, Thinh Nguyen, Khoa D Doan et al.2024 · 2 citationsarXiv
Retrospective Feature Estimation for Continual Learning2406.17381v2 · Nghia D. Nguyen, Hieu Trung Nguyen, Ang Li et al.2024 · 0 citationsarXiv
Composite Concept Extraction through Backdooring2406.13411v2 · Banibrata Ghosh, Haripriya Harikumar, Khoa D Doan et al.2024 · 0 citationsarXiv
Cold-start Recommendation by Personalized Embedding Region Elicitation2406.00973v1 · Hieu Trung Nguyen, Duy Nguyen, Khoa Doan et al.2024 · 0 citationsarXiv
Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models2312.03419v3 · Sze Jue Yang, Chinh D. La, Quang H. Nguyen et al.2023 · 0 citationsarXiv
Fooling the Textual Fooler via Randomizing Latent Representations2310.01452v2 · Duy C. Hoang, Quang H. Nguyen, Saurav Manchanda et al.2023 · 1 citationarXiv
Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks2310.00567v1 · Quang H. Nguyen, Yingjie Lao, Tung Pham et al.2023 · 2 citationsarXiv
Everyone Can Attack: Repurpose Lossy Compression as a Natural Backdoor Attack2308.16684v2 · Sze Jue Yang, Quang Nguyen, Chee Seng Chan et al.2023 · 0 citationsarXiv
A Cosine Similarity-based Method for Out-of-Distribution Detection2306.14920v1 · Nguyen Ngoc-Hieu, Nguyen Hung-Quang, The-Anh Ta et al.2023 · 3 citationsarXiv
Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions2303.02213v1 · Thuy Dung Nguyen, Tuan Nguyen, Phi Le Nguyen et al.2023 · 130 citationsarXiv
Asymmetric Hashing for Fast Ranking via Neural Network Measures2211.00619v1 · Khoa Doan, Shulong Tan, Weijie Zhao et al.2022 · 3 citationsarXiv
Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class2210.09194v1 · Khoa D. Doan, Yingjie Lao, Ping Li2022 · 20 citationsarXiv
CoopHash: Cooperative Learning of Multipurpose Descriptor and Contrastive Pair Generator via Variational MCMC Teaching for Supervised Image Hashing2210.04288v4 · Khoa D. Doan, Jianwen Xie, Yaxuan Zhu et al.2022 · 2 citationsarXiv
Defending Backdoor Attacks on Vision Transformer via Patch Processing2206.12381v2 · Khoa D. Doan, Yingjie Lao, Peng Yang et al.2022 · 20 citationsarXiv
One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching2205.15721v1 · Khoa D. Doan, Peng Yang, Ping Li2022 · 54 citationsarXiv
Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space2003.11774v2 · Khoa D. Doan, Saurav Manchanda, Fengjiao Wang et al.2020 · 4 citationsarXiv
Regression via Implicit Models and Optimal Transport Cost Minimization2003.01296v1 · Saurav Manchanda, Khoa Doan, Pranjul Yadav et al.2020 · 2 citationsarXiv
Image Hashing by Minimizing Discrete Component-wise Wasserstein Distance2003.00134v3 · Khoa D. Doan, Saurav Manchanda, Sarkhan Badirli et al.2020 · 4 citationsarXiv
Targeted display advertising: the case of preferential attachment2002.02879v1 · Saurav Manchanda, Pranjul Yadav, Khoa Doan et al.2020 · 3 citationsarXiv
Career total: 65 works. 47 are in this corpus.
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.