Data Science | Machine Learning with Python for Researchers
31.7K subscribers
1.93K photos
102 videos
22 files
2.21K links
Admin: @HusseinSheikho

The Data Science and Python channel is for researchers and advanced programmers

Buy ads: https://telega.io/c/dataScienceT
Download Telegram
🔹 Title: EpiCache: Episodic KV Cache Management for Long Conversational Question Answering

🔹 Publication Date: Published on Sep 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.17396
• PDF: https://arxiv.org/pdf/2509.17396

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: Synthetic bootstrapped pretraining

🔹 Publication Date: Published on Sep 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.15248
• PDF: https://arxiv.org/pdf/2509.15248

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

🔹 Publication Date: Published on Sep 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.17627
• PDF: https://arxiv.org/pdf/2509.17627
• Github: https://github.com/Phantom-video/OmniInsert

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

🔹 Publication Date: Published on Sep 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.16941
• PDF: https://arxiv.org/pdf/2509.16941
• Project Page: https://scale.com/research/swe_bench_pro

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: Mano Report

🔹 Publication Date: Published on Sep 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.17336
• PDF: https://arxiv.org/pdf/2509.17336

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: ARE: Scaling Up Agent Environments and Evaluations

🔹 Publication Date: Published on Sep 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.17158
• PDF: https://arxiv.org/pdf/2509.17158

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

🔹 Publication Date: Published on Sep 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.09873
• PDF: https://arxiv.org/pdf/2509.09873
• Project Page: https://huggingface.co/papers?q=GitHub%20projects

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
1
📌 Paper Walkthrough: Attention Is All You Need

🗂 Category: DEEP LEARNING

🕒 Date: 2024-11-03 | ⏱️ Read time: 46 min read

The complete guide to implementing a Transformer from scratch
1
🔹 Title: LIMI: Less is More for Agency

🔹 Publication Date: Published on Sep 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.17567
• PDF: https://arxiv.org/pdf/2509.17567
• Project Page: https://github.com/GAIR-NLP/LIMI
• Github: https://github.com/GAIR-NLP/LIMI

🔹 Datasets citing this paper:
https://huggingface.co/datasets/GAIR/LIMI

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes

🔹 Publication Date: Published on Sep 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.16415
• PDF: https://arxiv.org/pdf/2509.16415
• Project Page: https://aigeeksgroup.github.io/StereoAdapter/
• Github: https://github.com/AIGeeksGroup/StereoAdapter

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: Understanding Embedding Scaling in Collaborative Filtering

🔹 Publication Date: Published on Sep 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.15709
• PDF: https://arxiv.org/pdf/2509.15709

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
1
🔹 Title: AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

🔹 Publication Date: Published on Sep 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.17641
• PDF: https://arxiv.org/pdf/2509.17641
• Github: https://auditorybenchpp.github.io/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs

🔹 Publication Date: Published on Sep 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.16633
• PDF: https://arxiv.org/pdf/2509.16633
• Github: https://github.com/vl2g/MPA

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: From Uniform to Heterogeneous: Tailoring Policy Optimization to Every Token's Nature

🔹 Publication Date: Published on Sep 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.16591
• PDF: https://arxiv.org/pdf/2509.16591
• Github: https://github.com/starriver030515/HAPO

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction

🔹 Publication Date: Published on Sep 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.18095
• PDF: https://arxiv.org/pdf/2509.18095

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning

🔹 Publication Date: Published on Sep 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.17437
• PDF: https://arxiv.org/pdf/2509.17437

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

🔹 Publication Date: Published on Sep 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.17191
• PDF: https://arxiv.org/pdf/2509.17191

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

🔹 Publication Date: Published on Sep 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.18056
• PDF: https://arxiv.org/pdf/2509.18056

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

🔹 Publication Date: Published on Sep 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.17671
• PDF: https://arxiv.org/pdf/2509.17671

🔹 Datasets citing this paper:
https://huggingface.co/datasets/newmindai/RAGTruth-TR

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
https://t.iss.one/DataScienceT
🔹 Title: CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects

🔹 Publication Date: Published on Sep 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.14856
• PDF: https://arxiv.org/pdf/2509.14856

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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