✨COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling

📝 Summary:
COMPASS is a data-centric framework for multilingual LLM adaptation. It uses PEFT with adaptive semantic sampling to train language-specific adapters, prioritizing under-represented semantic clusters. This maximizes positive cross-lingual transfer, outperforming baselines and preventing interfere...

🔹 Publication Date: Published on Apr 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.20720
• PDF: https://arxiv.org/pdf/2604.20720

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

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

#MultilingualLLM #PEFT #NLP #DataCentricAI #MachineLearning

✨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

✨VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation

📝 Summary:
VLAA-GUI is a modular GUI agent framework that addresses early stopping and repetitive loop issues through integrated components for verification, loop breaking, and search capabilities. AI-generated ...

🔹 Publication Date: Published on Apr 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.21375
• PDF: https://arxiv.org/pdf/2604.21375
• Project Page: https://ucsc-vlaa.github.io/VLAA-GUI/
• Github: https://github.com/UCSC-VLAA/VLAA-GUI

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale

📝 Summary:
TingIS is an enterprise-grade incident discovery system that uses multi-stage event linking with LLMs, cascaded routing, and noise reduction to efficiently identify critical issues from high-volume, n...

🔹 Publication Date: Published on Apr 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.21889
• PDF: https://arxiv.org/pdf/2604.21889

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models

📝 Summary:
DAVinCI is a dual attribution and verification framework that enhances factual reliability and interpretability of large language models by attributing claims to internal components and external sourc...

🔹 Publication Date: Published on Apr 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.21193
• PDF: https://arxiv.org/pdf/2604.21193
• Github: https://github.com/vr25/davinci

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI

📝 Summary:
A novel variational autoencoder framework with supervised contrastive learning and discriminative disentanglement achieves superior performance in authorship attribution and AI-generated text detectio...

🔹 Publication Date: Published on Apr 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.21300
• PDF: https://arxiv.org/pdf/2604.21300
• Github: https://github.com/hieum98/avae

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks

📝 Summary:
A co-evolution framework enables large language models to discover, retain, and reuse structured skills across episodes in long-horizon interactive environments through a learnable skill bank and skil...

🔹 Publication Date: Published on Apr 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.20987
• PDF: https://arxiv.org/pdf/2604.20987
• Project Page: https://wuxiyang1996.github.io/COSPLAY_page/
• Github: https://wuxiyang1996.github.io/COSPLAY_page/

🔹 Models citing this paper:
• https://huggingface.co/IntelligenceLab/COS-PLAY

✨ Datasets citing this paper:
• https://huggingface.co/datasets/IntelligenceLab/Cos-Play-Cold-Start

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Hybrid Policy Distillation for LLMs

📝 Summary:
Hybrid Policy Distillation combines forward and reverse KL divergence approaches to improve knowledge distillation stability and efficiency across different model sizes and tasks. AI-generated summary...

🔹 Publication Date: Published on Apr 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.20244
• PDF: https://arxiv.org/pdf/2604.20244
• Github: https://github.com/zwhong714/Hybrid-Policy-Distillation

🔹 Models citing this paper:
• https://huggingface.co/wh-zhu/Qwen2.5-7B-PSFT-RL-DAPO-90
• https://huggingface.co/wh-zhu/qwen2.5-1.5B-longcot-reasoning-HPD

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning

📝 Summary:
WebGen-R1 is a reinforcement learning framework enabling small language models to generate functional and aesthetically pleasing multi-page websites. It uses structured generation and a novel cascaded multimodal reward for structural integrity, functional feedback, and aesthetic supervision. WebG...

🔹 Publication Date: Published on Apr 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.20398
• PDF: https://arxiv.org/pdf/2604.20398

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

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

#ReinforcementLearning #LLMs #WebsiteGeneration #AI #WebDevelopment

A trusted platform for cryptocurrency enthusiasts and reliable trading.

✨EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model

📝 Summary:
EditCrafter enables high-resolution image editing using pretrained text-to-image diffusion models through tiled inversion and noise-damped manifold-constrained guidance without requiring model tuning....

🔹 Publication Date: Published on Apr 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.10268
• PDF: https://arxiv.org/pdf/2604.10268
• Project Page: https://editcrafter.github.io/
• Github: https://github.com/EditCrafter/EditCrafter

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents

📝 Summary:
A knowledge graph-based external memory framework enhances language model personalization through dynamic semantic and temporal representations with diverse retrieval mechanisms. AI-generated summary ...

🔹 Publication Date: Published on Apr 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2506.17001
• PDF: https://arxiv.org/pdf/2506.17001

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research