✨UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction

📝 Summary:
UAGLNet addresses building extraction challenges by integrating global and local features through a hybrid CNN and transformer cooperative encoder, intermediate interaction block, and uncertainty-aggr...

🔹 Publication Date: Published on Dec 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.12941
• PDF: https://arxiv.org/pdf/2512.12941

🔹 Models citing this paper:
• https://huggingface.co/ldxxx/UAGLNet_Backbone
• https://huggingface.co/ldxxx/UAGLNet_Inria
• https://huggingface.co/ldxxx/UAGLNet_WHU

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates

📝 Summary:
VLMs struggle with error-prone vision-based sequential planning tasks, but Scene Graph Incremental updates (SGI) improves their performance by introducing intermediate reasoning steps. AI-generated su...

🔹 Publication Date: Published on Dec 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.10342
• PDF: https://arxiv.org/pdf/2512.10342

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Hierarchical Dataset Selection for High-Quality Data Sharing

📝 Summary:
DaSH selects entire datasets from diverse sources to boost ML performance. It models utility hierarchically, outperforming existing methods by up to 26.2 percent accuracy with fewer resources. DaSH is robust for multi-source learning workflows.

🔹 Publication Date: Published on Dec 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.10952
• PDF: https://arxiv.org/pdf/2512.10952

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Unveiling User Perceptions in the Generative AI Era: A Sentiment-Driven Evaluation of AI Educational Apps' Role in Digital Transformation of e-Teaching

📝 Summary:
User reviews of AI educational apps show predominantly positive sentiments, with homework helpers leading in accuracy and personalization. However, language and LMS apps lag due to instability and limited features. This highlights generative AIs potential for e-teaching despite challenges.

🔹 Publication Date: Published on Dec 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.11934
• PDF: https://arxiv.org/pdf/2512.11934
• Github: https://github.com/erfan-nourbakhsh/GenAI-EdSent

✨ Datasets citing this paper:
• https://huggingface.co/datasets/Erfan-Nourbakhsh/GenAI-EdSent

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Universal Reasoning Model

📝 Summary:
The Universal Reasoning Model URM enhances Universal Transformers with short convolution and truncated backpropagation. This approach substantially improves reasoning performance on ARC-AGI tasks, achieving state-of-the-art results.

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14693
• PDF: https://arxiv.org/pdf/2512.14693
• Github: https://github.com/zitian-gao/URM

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨VABench: A Comprehensive Benchmark for Audio-Video Generation

📝 Summary:
VABench is a benchmark framework for evaluating audio-video generation models, covering text-to-audio-video, image-to-audio-video, and stereo audio-video tasks with 15 evaluation dimensions. AI-genera...

🔹 Publication Date: Published on Dec 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.09299
• PDF: https://arxiv.org/pdf/2512.09299
• Github: https://github.com/tanABCC/VABench

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning

📝 Summary:
G2RL, a gradient-guided reinforcement learning framework, enhances exploration in large language models by leveraging the model's own update geometry, leading to improved performance on various reason...

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15687
• PDF: https://arxiv.org/pdf/2512.15687

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?

📝 Summary:
A benchmark evaluates the performance of vision-language models on understanding long-context information compressed into dense visual representations, revealing significant limitations in capturing l...

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15649
• PDF: https://arxiv.org/pdf/2512.15649
• Github: https://github.com/Moenupa/VTCBench

✨ Datasets citing this paper:
• https://huggingface.co/datasets/MLLM-CL/VTCBench

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SCOPE: Prompt Evolution for Enhancing Agent Effectiveness

📝 Summary:
SCOPE enhances LLM agents' context management through prompt evolution, improving task success rates in dynamic environments without human intervention. AI-generated summary Large Language Model (LLM)...

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15374
• PDF: https://arxiv.org/pdf/2512.15374
• Github: https://github.com/JarvisPei/SCOPE

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Simultaneous Tactile-Visual Perception for Learning Multimodal Robot Manipulation

📝 Summary:
TacThru-UMI, a system combining a TacThru sensor with a Transformer-based Diffusion Policy, achieves superior performance in robotic manipulation tasks by integrating simultaneous multimodal perceptio...

🔹 Publication Date: Published on Dec 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.09851
• PDF: https://arxiv.org/pdf/2512.09851
• Project Page: https://tacthru.yuyang.li/
• Github: https://github.com/YuyangLee/TacThru

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DEER: Draft with Diffusion, Verify with Autoregressive Models

📝 Summary:
DEER is a novel speculative decoding framework that uses diffusion large language models for drafting, overcoming limitations of autoregressive drafters. It achieves significantly longer draft acceptance lengths and much faster LLM decoding speeds, outperforming existing methods like EAGLE-3.

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15176
• PDF: https://arxiv.org/pdf/2512.15176

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning

📝 Summary:
Skyra, a specialized multimodal large language model, detects and explains visual artifacts in AI-generated videos using a novel dataset and two-stage training strategy, outperforming existing methods...

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15693
• PDF: https://arxiv.org/pdf/2512.15693
• Project Page: https://joeleelyf.github.io/Skyra/
• Github: https://github.com/JoeLeelyf/Skyra

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Fast and Accurate Causal Parallel Decoding using Jacobi Forcing

📝 Summary:
Jacobi Forcing is a progressive distillation method that enables efficient parallel decoding of transformer-based models while maintaining performance, significantly reducing inference latency. AI-gen...

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14681
• PDF: https://arxiv.org/pdf/2512.14681
• Github: https://github.com/hao-ai-lab/JacobiForcing

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

📝 Summary:
DiffusionVL, a family of diffusion vision language models derived from autoregressive models through fine-tuning, achieves performance improvements and faster inference speeds compared to existing mod...

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15713
• PDF: https://arxiv.org/pdf/2512.15713

🔹 Models citing this paper:
• https://huggingface.co/hustvl/DiffusionVL-Qwen2.5VL-3B
• https://huggingface.co/hustvl/DiffusionVL-Qwen2.5VL-7B

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

📝 Summary:
Qwen-Image-Layered decomposes images into semantically disentangled RGBA layers using a diffusion model, enabling independent editing of each layer and improving decomposition quality and consistency....

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15603
• PDF: https://arxiv.org/pdf/2512.15603

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Step-GUI Technical Report

📝 Summary:
A self-evolving training pipeline with the Calibrated Step Reward System and GUI-MCP protocol improve GUI automation efficiency, accuracy, and privacy in real-world scenarios. AI-generated summary Rec...

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15431
• PDF: https://arxiv.org/pdf/2512.15431

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Robust and Calibrated Detection of Authentic Multimedia Content

📝 Summary:
A resynthesis framework enhances deepfake detection by verifying authenticity with low false positive rates and robustness against efficient adversaries, supporting multiple modalities. AI-generated s...

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15182
• PDF: https://arxiv.org/pdf/2512.15182

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasets

📝 Summary:
Nano Banana Pro excels in subjective visual quality across low-level vision tasks without fine-tuning but struggles with traditional reference-based quantitative metrics due to generative model stocha...

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15110
• PDF: https://arxiv.org/pdf/2512.15110
• Project Page: https://lowlevelbanana.github.io/

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning

📝 Summary:
The paper proposes SAGE, a multi-turn reasoning system for video that mimics human behavior, using synthetic data and reinforcement learning to improve performance on long videos. AI-generated summary...

🔹 Publication Date: Published on Dec 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.13874
• PDF: https://arxiv.org/pdf/2512.13874
• Project Page: https://praeclarumjj3.github.io/sage/
• Github: https://github.com/allenai/SAGE

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨In Pursuit of Pixel Supervision for Visual Pre-training

📝 Summary:
Pixio, an enhanced masked autoencoder, demonstrates competitive performance across various downstream tasks using pixel-space self-supervised learning, outperforming latent-space approaches. AI-genera...

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.15715
• PDF: https://arxiv.org/pdf/2512.15715
• Project Page: https://github.com/facebookresearch/pixio
• Github: https://github.com/facebookresearch/pixio

🔹 Models citing this paper:
• https://huggingface.co/facebook/pixio-vitb16
• https://huggingface.co/facebook/pixio-vitl16
• https://huggingface.co/facebook/pixio-vit1b16

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research