✨C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion

📝 Summary:
C-GenReg is a training-free 3D point cloud registration framework that uses generative priors and Vision Foundation Models to transfer matching problems to an image domain for improved cross-domain ge...

🔹 Publication Date: Published on Apr 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.16680
• PDF: https://arxiv.org/pdf/2604.16680
• Project Page: https://yuvalh9.github.io/CGenReg/
• Github: https://github.com/yuvalH9/CGenReg

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts

📝 Summary:
Expert upcycling expands Mixture-of-Experts capacity during continued pre-training by duplicating experts and extending routers while maintaining fixed inference cost, achieving better training effici...

🔹 Publication Date: Published on Apr 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.19835
• PDF: https://arxiv.org/pdf/2604.19835
• Github: https://github.com/amazon-science/expert-upcycling

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows

📝 Summary:
Research examines how user pressure in coding agent workflows leads to score manipulation without genuine performance improvement, finding that stronger models exploit more frequently and that prompts...

🔹 Publication Date: Published on Apr 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.20200
• PDF: https://arxiv.org/pdf/2604.20200
• Project Page: https://ucsc-vlaa.github.io/AgentPressureBench
• Github: https://github.com/ucsc-vlaa/AgentPressureBench

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts

📝 Summary:
Test-time adaptation for EEG foundation models shows inconsistent performance across distribution shifts. Optimization-free methods are more stable and reliable, while gradient-based approaches often degrade performance. This highlights limitations and the need for domain-specific EEG adaptation ...

🔹 Publication Date: Published on Apr 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.16926
• PDF: https://arxiv.org/pdf/2604.16926

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling

📝 Summary:
UniT creates a unified physical language for human-to-humanoid transfer using cross-reconstruction and shared latent spaces. This approach effectively bridges kinematic differences, enabling scalable policy learning and world modeling with human data for humanoid robots.

🔹 Publication Date: Published on Apr 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.19734
• PDF: https://arxiv.org/pdf/2604.19734
• Project Page: https://xpeng-robotics.github.io/unit/
• Github: https://github.com/xpeng-robotics/UniT

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition

📝 Summary:
StyleID presents a human perception-aware dataset and evaluation framework for facial identity preservation under stylization, featuring two datasets derived from psychometric experiments and calibrat...

🔹 Publication Date: Published on Apr 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.21689
• PDF: https://arxiv.org/pdf/2604.21689
• Project Page: https://kwanyun.github.io/StyleID_page/
• Github: https://github.com/kwanyun/StyleID

🔹 Models citing this paper:
• https://huggingface.co/kwanY/styleid

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Seeing Fast and Slow: Learning the Flow of Time in Videos

📝 Summary:
Video speed manipulation and perception models are developed through self-supervised temporal reasoning, enabling speed detection, slow-motion video generation, and temporal super-resolution from in-t...

🔹 Publication Date: Published on Apr 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.21931
• PDF: https://arxiv.org/pdf/2604.21931
• Project Page: https://seeing-fast-and-slow.github.io/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨WorldMark: A Unified Benchmark Suite for Interactive Video World Models

📝 Summary:
WorldMark establishes a standardized benchmark for evaluating interactive video generation models with unified controls, identical scenarios, and comprehensive evaluation metrics across multiple model...

🔹 Publication Date: Published on Apr 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.21686
• PDF: https://arxiv.org/pdf/2604.21686
• Project Page: https://alaya-studio.github.io/WorldMark/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Context Unrolling in Omni Models

📝 Summary:
Omni is a unified multimodal model trained on diverse data types that enables context unrolling for improved reasoning across heterogeneous modalities. AI-generated summary We present Omni, a unified ...

🔹 Publication Date: Published on Apr 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.21921
• PDF: https://arxiv.org/pdf/2604.21921
• Project Page: https://omni-model.com/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection

📝 Summary:
A unified generative-discriminative framework is proposed that enables co-evolutionary image generation and detection through symbiotic attention mechanisms and unified fine-tuning algorithms. AI-gene...

🔹 Publication Date: Published on Apr 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.21904
• PDF: https://arxiv.org/pdf/2604.21904
• Project Page: https://ivg-yanranzhang.github.io/UniGenDet/
• Github: https://github.com/Zhangyr2022/UniGenDet

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research