DS
Daniel Sonntag
cs.CVcs.LGcs.HCcs.AIcs.CLeess.IVcs.ROeye trackingcs.IRmachine learning
On Valency
published · living versionsW_9yx7tx3d·v1 · currentpublished
Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution
with Pham Tri Quang, Bao-Ngoc Dao, Minh Duc Nguyen, Duc-Duy Nguyen +13
1 version
W_k2zhmf35·v1published
Preprints & journals
87 papers in the corpus · 2008–2026Progress-Guided Preference Generation for Aligning Generative Control Policies2610.25692v1 · Tung M. Luu, Tri Ton, Duc M. Nguyen et al.2026 · 0 citationsarXivon Valency
What Do Visual-Head Discovery Scores Actually Find? Attention Source, Necessity, and Random-Control Pitfalls in Vision-Language Models2610.13111v1 · Md Abdul Kadir, Daniel Sonntag2026 · 0 citationsarXiv
Where Do LLMs Retrieve Network Information? Identifying the Responsible Heads and Neurons2610.08200v3 · Md Abdul Kadir, Md Mohasin Hossain, Omair Shahzad Bhatti et al.2026 · 0 citationsarXiv
EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards2609.29230v1 · Omar Adjali, Siting Liang, Omair Shahzad Bhatti et al.2026 · 0 citationsarXiv
FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational Pathology2609.27710v2 · Anh-Tien Nguyen, Trung DQ. Dang, Nghiem Tuong Diep et al.2026 · 0 citationsarXiv
Evaluating Explanation-Driven Vision-Language Reasoning via Generation Order Interventions2609.29496v1 · Siting Liang, Luca Rippe, Omar Adjali et al.2026 · 0 citationsarXiv
A Multi-Domain and Multi-Task Generative Framework with Explicit Task and Domain Conditioning for Cross-Domain Event Extraction2608.23235v1 · Siting Liang, Omar Adjali, Daniel Sonntag2026 · 0 citationsarXiv
A Scalable Cross-Domain Event Extraction System via a Unified Generative Training Framework2608.23261v1 · Siting Liang, Omar Adjali, Omair Shahzad Bhatti et al.2026 · 0 citationsarXiv
Beyond Heatmaps: Unsupervised Concept-Graph Reasoning for Interpretable Visual Explanation2607.01416v2 · Md Mohasin Hossain, Anar Amirli, Robert Leist et al.2026 · 0 citationsarXiv
TRACE: A Concept Bottleneck Model for Longitudinal 3D Glioblastoma Response Assessment2606.30313v2 · Alia Tarek, Hamsa Saberr, Hamza Elghonemy 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
Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think2606.20246v2 · Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha 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
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
FunduScope: a human-centered, machine learning-based interactive tool for training junior ophthalmologists in diabetic retinopathy detection.41909878 · Bittner, Sara-Jane, Barz, Michael, Sonntag, Daniel2026 · 1 citationFrontiers in big data. 2026;9:1676922
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models2603.07307v2 · Duy M. H. Nguyen, Tuan A. Tran, Duong Nguyen et al.2026 · 0 citationsarXiv
Heads Up!: Towards In Situ Photogrammetry Annotations and Augmented Reality Visualizations for Guided Backcountry Skiing2602.21771v1 · Christoph Albert Johns, L'aszl'o Kop'acsi, Michael Barz et al.2026 · 0 citationsarXiv
The Speed-up Factor: A Quantitative Multi-Iteration Active Learning Performance Metric2602.13359v1 · Hannes Kath, Thiago S. Gouvea, Daniel Sonntag2026 · 0 citationsH. Kath, T.S. Gouv\^ea, D. Sonntag (2026). The Speed-up Factor: A Quantitative Multi-Iteration Active Learning Performance Metric. Transactions on Machine Learning Research
Asynchronous federated learning for web-based OCT image analysis.41497559 · Alam, Hasan Md Tusfiqur, Maurer, Tim, Mohamed Selim, Abdulrahman et al.2026 · 2 citationsJournal of medical imaging (Bellingham, Wash.). 2026;13(1):014501
Reinforcing Trustworthiness in Multimodal Emotional Support Systems2511.10011v2 · Huy M. Le, Dat Tien Nguyen, Ngan T. T. Vo et al.2025 · 0 citationsarXiv
How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?2511.05449v1 · Tuan Anh Tran, Duy M. H. Nguyen, Hoai-Chau Tran et al.2025 · 1 citationarXiv
S-Chain: Structured Visual Chain-of-Thought For Medicine2510.22728v1 · Khai Le-Duc, Duy M. H. Nguyen, Phuong T. H. Trinh et al.2025 · 2 citationsarXiv
eyeNotate: Interactive Annotation of Mobile Eye Tracking Data Based on Few-Shot Image Classification.40708803 · Barz, Michael, Bhatti, Omair Shahzad, Alam, Hasan Md Tusfiqur et al.2025 · 2 citationsJournal of eye movement research. 2025;18(4):27
Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling2506.08681v2 · Phuc Minh Nguyen, Ngoc-Hieu Nguyen, Duy H. M. Nguyen et al.2025 · 1 citationarXiv
Your Interface, Your Control: Adapting Takeover Requests for Seamless Handover in Semi-Autonomous Vehicles2506.01836v1 · Amr Gomaa, Simon Engel, Elena Meiser et al.2025 · 0 citationsarXiv
CBM-RAG: Demonstrating Enhanced Interpretability in Radiology Report Generation with Multi-Agent RAG and Concept Bottleneck Models2504.20898v2 · Hasan Md Tusfiqur Alam, Devansh Srivastav, Abdulrahman Mohamed Selim et al.2025 · 4 citationsarXiv
I-MPN: inductive message passing network for efficient human-in-the-loop annotation of mobile eye tracking data.40268979 · Le, Hoang H, Nguyen, Duy M H, Bhatti, Omair Shahzad et al.2025 · 1 citationScientific reports. 2025;15(1):14192
InFL-UX: A Toolkit for Web-Based Interactive Federated Learning2503.04318v2 · Tim Maurer, Abdulrahman Mohamed Selim, Hasan Md Tusfiqur Alam et al.2025 · 0 citationsarXiv
MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classification2502.07409v5 · Anh-Tien Nguyen, Duy Minh Ho Nguyen, Nghiem Tuong Diep et al.2025 · 0 citationsTransactions on Machine Learning Research (09/2025)
On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation2502.03029v3 · Nghiem T. Diep, Huy Nguyen, Chau Nguyen et al.2025 · 0 citationsarXiv
Deep Learning for Ophthalmology: The State-of-the-Art and Future Trends2501.04073v1 · Duy M. H. Nguyen, Hasan Md Tusfiqur Alam, Tai Nguyen et al.2025 · 2 citationsarXiv
Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAG2412.16086v2 · Hasan Md Tusfiqur Alam, Devansh Srivastav, Md Abdul Kadir et al.2024 · 16 citationsLecture Notes in Computer Science (LNCS) 2025, Volume 15574
ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models2410.02615v4 · Duy M. H. Nguyen, Nghiem T. Diep, Trung Q. Nguyen et al.2024 · 1 citationarXiv
Enhancing Journalism with AI: A Study of Contextualized Image Captioning for News Articles using LLMs and LMMs2408.04331v1 · Aliki Anagnostopoulou, Thiago Gouvea, Daniel Sonntag2024 · 2 citationsarXiv
Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model2407.04489v1 · Duy M. H. Nguyen, An T. Le, Trung Q. Nguyen et al.2024 · 0 citationsarXiv
A look under the hood of the Interactive Deep Learning Enterprise (No-IDLE)2406.19054v1 · Daniel Sonntag, Michael Barz, Thiago Gouvea2024 · 1 citationarXiv
A review of machine learning in scanpath analysis for passive gaze-based interaction.38903158 · Mohamed Selim, Abdulrahman, Barz, Michael, Bhatti, Omair Shahzad et al.2024 · 20 citationsFrontiers in artificial intelligence. 2024;7:1391745
Accelerating Transformers with Spectrum-Preserving Token Merging2405.16148v2 · Hoai-Chau Tran, Duy M. H. Nguyen, Duy M. Nguyen et al.2024 · 13 citationsarXiv
Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoors2403.16569v1 · Md Abdul Kadir, GowthamKrishna Addluri, Daniel Sonntag2024 · 0 citationsarXiv
Modular Deep Active Learning Framework for Image Annotation: A Technical Report for the Ophthalmo-AI Project2403.15143v1 · Md Abdul Kadir, Hasan Md Tusfiqur Alam, Pascale Maul et al.2024 · 0 citationsarXiv
Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks2402.01975v3 · Duy M. H. Nguyen, Nina Lukashina, Tai Nguyen et al.2024 · 2 citationsarXiv
On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation2311.11096v1 · Duy Minh Ho Nguyen, Tan Ngoc Pham, Nghiem Tuong Diep et al.2023 · 4 citationsarXiv
EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation2307.10745v2 · Md Abdul Kadir, Hasan Md Tusfiqur Alam, Daniel Sonntag2023 · 6 citationsarXiv
Harmonizing Feature Attributions Across Deep Learning Architectures: Enhancing Interpretability and Consistency2307.02150v3 · Md Abdul Kadir, Gowtham Krishna Addluri, Daniel Sonntag2023 · 6 citationsGerman Conference on Artificial Intelligence 2023
LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching2306.11925v3 · Duy M. H. Nguyen, Hoang Nguyen, Nghiem T. Diep et al.2023 · 38 citationsarXiv
Putting Humans in the Image Captioning Loop2306.03476v1 · Aliki Anagnostopoulou, Mareike Hartmann, Daniel Sonntag2023 · 0 citationsarXiv
Towards Adaptable and Interactive Image Captioning with Data Augmentation and Episodic Memory2306.03500v1 · Aliki Anagnostopoulou, Mareike Hartmann, Daniel Sonntag2023 · 1 citationarXiv
Cross-Viewpoint Semantic Mapping: Integrating Human and Robot Perspectives for Improved 3D Semantic Reconstruction.37299853 · Kopácsi, László, Baffy, Benjámin, Baranyi, Gábor et al.2023 · 4 citationsSensors (Basel, Switzerland). 2023;23(11)
A Deep Generative Model for Interactive Data Annotation through Direct Manipulation in Latent Space2305.15337v1 · Hannes Kath, Thiago S. Gouvea, Daniel Sonntag2023 · 1 citationarXiv
A Virtual Reality Tool for Representing, Visualizing and Updating Deep Learning Models2305.15353v1 · Hannes Kath, Bengt Luers, Thiago S. Gouvea et al.2023 · 2 citationsarXiv
Career total: 315 works. 87 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.