ML Research Hub
@DataScienceT
32.9K subscribers
4.72K photos
291 videos
24 files
5.1K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
About
Blog
Apps
Platform
Join
ML Research Hub
32.9K subscribers
ML Research Hub
🔹 Title: PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

🔹 Publication Date: Published on Aug 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17188
• PDF: https://arxiv.org/pdf/2508.17188

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
492 views
Explore Data Science
ML Research Hub
🔹 Title: InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18265
• PDF: https://arxiv.org/pdf/2508.18265
• Github: https://github.com/OpenGVLab/InternVL

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
357 views
Explore Data Science
ML Research Hub
🔹 Title: UQ: Assessing Language Models on Unsolved Questions

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17580
• PDF: https://arxiv.org/pdf/2508.17580
• Project Page: https://huggingface.co/datasets/uq-project/uq

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/uq-project/uq

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

For more data science resources:
✓ https://t.me/DataScienceT
311 views
Explore Data Science
ML Research Hub
🔹 Title: ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18190
• PDF: https://arxiv.org/pdf/2508.18190
• Github: https://github.com/weAIDB/ST-Raptor

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
282 views
Explore Data Science
ML Research Hub
🔹 Title: SpotEdit: Evaluating Visually-Guided Image Editing Methods

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18159
• PDF: https://arxiv.org/pdf/2508.18159
• Github: https://github.com/SaraGhazanfari/SpotEdit

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
280 views
Explore Data Science
ML Research Hub
🔹 Title: Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18076
• PDF: https://arxiv.org/pdf/2508.18076

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
331 views
Explore Data Science
ML Research Hub
🔹 Title: Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

🔹 Publication Date: Published on Aug 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.16949
• PDF: https://arxiv.org/pdf/2508.16949

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
307 views
Explore Data Science
ML Research Hub
🔹 Title: Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18032
• PDF: https://arxiv.org/pdf/2508.18032

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
❤1
335 views
Explore Data Science
ML Research Hub
🔹 Title: T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

🔹 Publication Date: Published on Aug 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17472
• PDF: https://arxiv.org/pdf/2508.17472

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
❤1
354 views
Explore Data Science
ML Research Hub
🔹 Title: TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

🔹 Publication Date: Published on Aug 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.16790
• PDF: https://arxiv.org/pdf/2508.16790

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
456 views
Explore Data Science
ML Research Hub
🔹 Title: Explain Before You Answer: A Survey on Compositional Visual Reasoning

🔹 Publication Date: Published on Aug 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17298
• PDF: https://arxiv.org/pdf/2508.17298
• Project Page: https://github.com/pokerme7777/Compositional-Visual-Reasoning-Survey
• Github: https://github.com/pokerme7777/Compositional-Visual-Reasoning-Survey

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
381 views
Explore Data Science
ML Research Hub
🔹 Title: Agent Lightning: Train ANY AI Agents with Reinforcement Learning

🔹 Publication Date: Published on Aug 5

🔹 Abstract: Agent Lightning is a flexible RL framework for training LLMs in various agents, using a hierarchical RL algorithm and decoupling execution from training to handle complex interactions. AI-generated summary We present Agent Lightning, a flexible and extensible framework that enables Reinforcement Learning (RL)-based training of Large Language Models (LLMs) for any AI agent. Unlike existing methods that tightly couple RL training with agent or rely on sequence concatenation with masking, Agent Lightning achieves complete decoupling between agent execution and training, allowing seamless integration with existing agents developed via diverse ways (e.g., using frameworks like LangChain, OpenAI Agents SDK, AutoGen, and building from scratch) with almost ZERO code modifications. By formulating agent execution as Markov decision process , we define an unified data interface and propose a hierarchical RL algorithm , LightningRL, which contains a credit assignment module, allowing us to decompose trajectories generated by ANY agents into training transition. This enables RL to handle complex interaction logic, such as multi-agent scenarios and dynamic workflows. For the system design, we introduce a Training-Agent Disaggregation architecture , and brings agent observability frameworks into agent runtime, providing a standardized agent finetuning interface. Experiments across text-to-SQL , retrieval-augmented generation, and math tool-use tasks demonstrate stable, continuous improvements, showcasing the framework's potential for real-world agent training and deployment.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.03680

• PDF: https://arxiv.org/pdf/2508.03680

• Project Page: https://www.microsoft.com/en-us/research/project/agent-lightning/

• Github: https://github.com/microsoft/agent-lightning

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
416 views
ML Research Hub
🔹 Title: MV-RAG: Retrieval Augmented Multiview Diffusion

🔹 Publication Date: Published on Aug 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.16577
• PDF: https://arxiv.org/pdf/2508.16577
• Project Page: https://yosefdayani.github.io/MV-RAG/
• Github: https://github.com/yosefdayani/MV-RAG

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
437 views
Explore Data Science
ML Research Hub
🔹 Title: MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

🔹 Publication Date: Published on Aug 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17290
• PDF: https://arxiv.org/pdf/2508.17290

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
❤1
415 views
Explore Data Science
ML Research Hub
🔹 Title: German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17973
• PDF: https://arxiv.org/pdf/2508.17973

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
❤1
404 views
Explore Data Science
ML Research Hub
🔹 Title: Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

🔹 Publication Date: Published on Aug 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.16745
• PDF: https://arxiv.org/pdf/2508.16745

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
❤1
453 views
Explore Data Science
ML Research Hub
🔹 Title: Limitations of Normalization in Attention Mechanism

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17821
• PDF: https://arxiv.org/pdf/2508.17821

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
569 views
Explore Data Science
ML Research Hub
🔹 Title: MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17811
• PDF: https://arxiv.org/pdf/2508.17811
• Project Page: https://hanzhichang.github.io/meshsplat_web
• Github: https://hanzhichang.github.io/meshsplat_web

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
❤1
556 views
Explore Data Science
ML Research Hub
🔹 Title: REGEN: Real-Time Photorealism Enhancement in Games via a Dual-Stage Generative Network Framework

🔹 Publication Date: Published on Aug 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17061
• PDF: https://arxiv.org/pdf/2508.17061
• Github: https://github.com/stefanos50/REGEN

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
❤2
532 views
Explore Data Science
ML Research Hub
Forwarded from ENG. Hussein Sheikho
🔍 Searching for fast, reliable proxies for your data science and machine learning projects?
Thordata provides the perfect solution for all your data scraping needs!
👍 https://www.thordata.com/?ls=DhthVzyG&lk=Data

✨ Why Choose Thordata?

✅ Rotating & Sticky Residential Proxies:
Enjoy secure, uninterrupted scraping with our rotating and sticky IPs.
Perfect for avoiding blocks and handling high-volume requests.
🌍 Global Coverage:
Access over 195 countries with advanced targeting options to pinpoint your ideal IPs, whether by country, state, city, or ASN.
⚡️ High-Speed Performance:
Get access to unlimited bandwidth and a 99.9% uptime guarantee—ideal for seamless, fast data collection.
💡 Flexible Usage:
Support for SOCKS5 and HTTP(S) protocols, ensuring compatibility with all your favorite scraping tools and services.

🎯 How to Get Started:
1️⃣ Join our official Telegram community.
2️⃣ Register and contact the admin @Thordata to activate your trial.
3️⃣ Receive 100MB of FREE Residential Proxy traffic to kickstart your scraping journey.

👉 Join now: https://t.me/thordataproxy

🔧 Start experiencing Thordata’s https://www.thordata.com/?ls=DhthVzyG&lk=Data power in your data science workflows today!
Whether it’s market research, machine learning, or competitive analysis—Thordata is your trusted partner in efficient, scalable data scraping.
Please open Telegram to view this post
VIEW IN TELEGRAM
Thordata
Thordata - High-Quality Proxy Service for Web Data Scraping
Thordata's precision proxy solution was chosen to ensure seamless data collection. Enjoy the best prices and services tailored to your needs.
❤4
576 views
ML Research Hub
🔹 Title: If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition

🔹 Publication Date: Published on Aug 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.16838
• PDF: https://arxiv.org/pdf/2508.16838
• Github: https://github.com/dipta007/De-Presuppose

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
✓ https://t.me/DataScienceT
493 views
Explore Data Science