ML Research Hub – Telegram
ML Research Hub
32.8K subscribers
4.14K photos
249 videos
23 files
4.47K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
🔹 Title: EdiVal-Agent: An Object-Centric Framework for Automated, Scalable, Fine-Grained Evaluation of Multi-Turn Editing

🔹 Publication Date: Published on Sep 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.13399
• PDF: https://arxiv.org/pdf/2509.13399
• Github: https://tianyucodings.github.io/EdiVAL-page/

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
1
🌟 Swiftproxy – Fast, Secure, and Reliable Proxies for Every Project

Looking for proxies that are stable, high-speed, and ready for any online task? Swiftproxy is your go-to solution! From web scraping and data analytics to automation and competitive research, our proxies help you work smarter, faster, and without limits.
🌐 https://www.swiftproxy.net/?ref=python53

Why Swiftproxy Stands Out:

🔄 Rotating & Sticky IPs

Switch IPs seamlessly or maintain the same one for longer sessions. Avoid blocks, CAPTCHAs, and interruptions effortlessly.

🌍 Global Coverage & Advanced Targeting
Access over 90 million IPs across 220+ countries. Pinpoint IPs by country, city, or ASN for precise data collection.

⚡️ Fast, Secure, & Reliable

Enjoy high-speed servers with 99.8% uptime and advanced encryption, ensuring seamless and secure data collection.

💻 Flexible & Compatible
Supports HTTP(S) and SOCKS5 protocols and integrates easily with over 650 tools and applications.

Flexible Data Usage
Residential proxies: Non-expiring bandwidth starting from just $0.7/GB — use it whenever you need.
Static residential proxies: Valid for 30 days, priced from $6/IP, giving you maximum control.

🔥Kickstart your projects with Swiftproxy’s reliable residential proxies and make your workflow smoother than ever!
👉 https://www.swiftproxy.net/?ref=python53

🎯 Get Started Quickly:
1. Register a new account on Swiftproxy
2. Contact support to claim 500MB free residential proxy traffic
🎊Use exclusive code SWIFT90 for 10% off your first purchase!

💫Join Swiftproxy Now: https://news.1rj.ru/str/swiftproxynetofficial
5
🔹 Title: MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

🔹 Publication Date: Published on Sep 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.16197
• PDF: https://arxiv.org/pdf/2509.16197

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

🔹 Publication Date: Published on Sep 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.15123
• PDF: https://arxiv.org/pdf/2509.15123

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent

🔹 Publication Date: Published on Sep 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.15566
• PDF: https://arxiv.org/pdf/2509.15566

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

🔹 Publication Date: Published on Sep 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.16198
• PDF: https://arxiv.org/pdf/2509.16198

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: BaseReward: A Strong Baseline for Multimodal Reward Model

🔹 Publication Date: Published on Sep 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.16127
• PDF: https://arxiv.org/pdf/2509.16127

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Lynx: Towards High-Fidelity Personalized Video Generation

🔹 Publication Date: Published on Sep 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.15496
• PDF: https://arxiv.org/pdf/2509.15496
• Project Page: https://byteaigc.github.io/Lynx/

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers

🔹 Publication Date: Published on Sep 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.10452
• PDF: https://arxiv.org/pdf/2509.10452

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

🔹 Publication Date: Published on Sep 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.15937
• PDF: https://arxiv.org/pdf/2509.15937
• Project Page: https://vlac.intern-ai.org.cn/
• Github: https://github.com/InternRobotics/VLAC

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents

🔹 Publication Date: Published on Sep 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.15233
• PDF: https://arxiv.org/pdf/2509.15233

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: SPATIALGEN: Layout-guided 3D Indoor Scene Generation

🔹 Publication Date: Published on Sep 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.14981
• PDF: https://arxiv.org/pdf/2509.14981
• Project Page: https://manycore-research.github.io/SpatialGen
• Github: https://github.com/manycore-research/SpatialGen

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue

🔹 Publication Date: Published on Sep 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.15061
• PDF: https://arxiv.org/pdf/2509.15061

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

🔹 Publication Date: Published on Sep 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.15591
• PDF: https://arxiv.org/pdf/2509.15591
• Project Page: https://zinanlin.me/blogs/latent_zoning_networks.html
• Github: https://github.com/microsoft/latent-zoning-networks

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
1
🔹 Title: Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems

🔹 Publication Date: Published on Sep 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.13989
• PDF: https://arxiv.org/pdf/2509.13989

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
1
🔹 Title: Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech

🔹 Publication Date: Published on Sep 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.14627
• PDF: https://arxiv.org/pdf/2509.14627
• Project Page: https://kimtaesu24.github.io/
• Github: https://github.com/kimtaesu24/MSenC

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing

🔹 Publication Date: Published on Sep 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.16622
• PDF: https://arxiv.org/pdf/2509.16622

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

🔹 Publication Date: Published on Sep 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.16596
• PDF: https://arxiv.org/pdf/2509.16596

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: DiffusionNFT: Online Diffusion Reinforcement with Forward Process

🔹 Publication Date: Published on Sep 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.16117
• PDF: https://arxiv.org/pdf/2509.16117

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System

🔹 Publication Date: Published on Sep 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.18091
• PDF: https://arxiv.org/pdf/2509.18091

🔹 Datasets citing this paper:
No datasets found

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

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