ML Research Hub – Telegram
ML Research Hub
32.7K subscribers
4.05K photos
234 videos
23 files
4.37K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
🔹 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://news.1rj.ru/str/DataScienceT
🔹 Title: MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18264
• PDF: https://arxiv.org/pdf/2508.18264
• Project Page: https://project.ironieser.cc/mmtok

🔹 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: Hermes 4 Technical Report

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18255
• PDF: https://arxiv.org/pdf/2508.18255
• Project Page: https://hermes4.nousresearch.com/

🔹 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: Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing

🔹 Publication Date: Published on Aug 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17326
• PDF: https://arxiv.org/pdf/2508.17326
• Github: https://github.com/tristan-deep/semantic-diffusion-echo-dehazing

🔹 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: Understanding Tool-Integrated Reasoning

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19201
• PDF: https://arxiv.org/pdf/2508.19201
• Project Page: https://zhongwenxu.notion.site/Understanding-Tool-Integrated-Reasoning-2551c4e140e3805489fadcc802a1ea83

🔹 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: Spacer: Towards Engineered Scientific Inspiration

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17661
• PDF: https://arxiv.org/pdf/2508.17661
• Github: https://github.com/asteromorph-corp/spacer

🔹 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: VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19247
• PDF: https://arxiv.org/pdf/2508.19247
• Project Page: https://huanngzh.github.io/VoxHammer-Page/
• Github: https://github.com/Nelipot-Lee/VoxHammer/Edit3D-Bench

🔹 Datasets citing this paper:
https://huggingface.co/datasets/huanngzh/Edit3D-Bench

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
1
🔹 Title: Unraveling the cognitive patterns of Large Language Models through module communities

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18192
• PDF: https://arxiv.org/pdf/2508.18192

🔹 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
2
ML Research Hub pinned «🔍 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…»
🔹 Title: OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19209
• PDF: https://arxiv.org/pdf/2508.19209
• Project Page: https://omnihuman-lab.github.io/v1_5/

🔹 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: UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18756
• PDF: https://arxiv.org/pdf/2508.18756
• Github: https://github.com/ZihaoHuang-notabot/Ultra-Sparse-Memory-Network

🔹 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: CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18124
• PDF: https://arxiv.org/pdf/2508.18124
• Github: https://github.com/CMPhysBench/CMPhysBench%5D

🔹 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: TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

🔹 Publication Date: Published on Aug 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17445
• PDF: https://arxiv.org/pdf/2508.17445

🔹 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: Wan-S2V: Audio-Driven Cinematic Video Generation

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18621
• PDF: https://arxiv.org/pdf/2508.18621

🔹 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: QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

🔹 Publication Date: Published on Aug 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.16697
• PDF: https://arxiv.org/pdf/2508.16697

🔹 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: ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2502.18080
• PDF: https://arxiv.org/pdf/2508.18773

🔹 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: Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.00910
• PDF: https://arxiv.org/pdf/2508.18370

🔹 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: FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19188
• PDF: https://arxiv.org/pdf/2508.19188
• Project Page: https://jhkim0759.github.io/projects/FastMesh/

🔹 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: Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

🔹 Publication Date: Published on Aug 6

🔹 Abstract: A structured framework and datasets for training customer service agents using well-defined support strategies improve the quality of customer support interactions and problem resolution. AI-generated summary Effective customer support requires not only accurate problem solving but also structured and empathetic communication aligned with professional standards. However, existing dialogue datasets often lack strategic guidance, and real-world service data is difficult to access and annotate. To address this, we introduce the task of Customer Support Conversation (CSC), aimed at training customer service agents to respond using well-defined support strategies. We propose a structured CSC framework grounded in COPC guidelines , defining five conversational stages and twelve strategies to guide high-quality interactions. Based on this, we construct CSConv , an evaluation dataset of 1,855 real-world customer-agent conversations rewritten using LLMs to reflect deliberate strategy use, and annotated accordingly. Additionally, we develop a role-playing approach that simulates strategy-rich conversations using LLM-powered roles aligned with the CSC framework, resulting in the training dataset RoleCS . Experiments show that fine-tuning strong LLMs on RoleCS significantly improves their ability to generate high-quality, strategy-aligned responses on CSConv . Human evaluations further confirm gains in problem resolution. All code and data will be made publicly available at https://github.com/aliyun/qwen-dianjin.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.04423

• PDF: https://arxiv.org/pdf/2508.04423

• Github: https://github.com/aliyun/qwen-dianjin

🔹 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: Autoregressive Universal Video Segmentation Model

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19242
• PDF: https://arxiv.org/pdf/2508.19242

🔹 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: MovieCORE: COgnitive REasoning in Movies

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19026
• PDF: https://arxiv.org/pdf/2508.19026
• Github: https://joslefaure.github.io/assets/html/moviecore.html

🔹 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