ML Research Hub – Telegram
ML Research Hub
32.8K subscribers
4.44K photos
272 videos
23 files
4.8K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
🔹 Title: Pathology-CoT: Learning Visual Chain-of-Thought Agent from Expert Whole Slide Image Diagnosis Behavior

🔹 Publication Date: Published on Oct 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.04587
• PDF: https://arxiv.org/pdf/2510.04587

🔹 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: Demystifying Reinforcement Learning in Agentic Reasoning

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11701
• PDF: https://arxiv.org/pdf/2510.11701
• Project Page: https://huggingface.co/collections/Gen-Verse/open-agentrl-68eda4c05755ca5a8c663656
• Github: https://github.com/Gen-Verse/Open-AgentRL

🔹 Datasets citing this paper:
https://huggingface.co/datasets/Gen-Verse/Open-AgentRL-SFT-3K
https://huggingface.co/datasets/Gen-Verse/Open-AgentRL-30K

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: Making Mathematical Reasoning Adaptive

🔹 Publication Date: Published on Oct 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.04617
• PDF: https://arxiv.org/pdf/2510.04617
• Github: https://github.com/LaiZhejian/AdaR

🔹 Datasets citing this paper:
https://huggingface.co/datasets/DreamW1ngs/AdaR-orca-math-9k

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09541
• PDF: https://arxiv.org/pdf/2510.09541
• Github: https://github.com/facebookresearch/SPG

🔹 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: Skill-Targeted Adaptive Training

🔹 Publication Date: Published on Oct 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.10023
• PDF: https://arxiv.org/pdf/2510.10023

🔹 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: The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09905
• PDF: https://arxiv.org/pdf/2510.09905

🔹 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: QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11696
• PDF: https://arxiv.org/pdf/2510.11696
• Project Page: https://github.com/NVlabs/QeRL
• Github: https://github.com/NVlabs/QeRL

🔹 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: DocReward: A Document Reward Model for Structuring and Stylizing

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11391
• PDF: https://arxiv.org/pdf/2510.11391

🔹 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: Graph Diffusion Transformers are In-Context Molecular Designers

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08744
• PDF: https://arxiv.org/pdf/2510.08744
• Github: https://github.com/liugangcode/DemoDiff

🔹 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: LLaMAX2: Your Translation-Enhanced Model also Performs Well in Reasoning

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09189
• PDF: https://arxiv.org/pdf/2510.09189

🔹 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: Diffusion Transformers with Representation Autoencoders

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11690
• PDF: https://arxiv.org/pdf/2510.11690

🔹 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: AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration

🔹 Publication Date: Published on Oct 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.10395
• PDF: https://arxiv.org/pdf/2510.10395
• Project Page: https://avocado-captioner.github.io/
• Github: https://github.com/AVoCaDO-Captioner/AVoCaDO

🔹 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: DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11712
• PDF: https://arxiv.org/pdf/2510.11712
• Project Page: https://fenghora.github.io/DiT360-Page/
• Github: https://fenghora.github.io/DiT360-Page/

🔹 Datasets citing this paper:
https://huggingface.co/datasets/Insta360-Research/Matterport3D_polished

🔹 Spaces citing this paper:
https://huggingface.co/spaces/Insta360-Research/DiT360
==================================

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

🔹 Publication Date: Published on Oct 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.10689
• PDF: https://arxiv.org/pdf/2510.10689

🔹 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: Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11027
• PDF: https://arxiv.org/pdf/2510.11027
• Project Page: https://internvl.github.io/blog/2025-10-11-Vlaser/
• Github: https://github.com/OpenGVLab/Vlaser/

🔹 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: GIR-Bench: Versatile Benchmark for Generating Images with Reasoning

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11026
• PDF: https://arxiv.org/pdf/2510.11026
• Project Page: https://hkust-longgroup.github.io/GIR-Bench/
• Github: https://github.com/HKUST-LongGroup/GIR-Bench/tree/main?tab=readme-ov-file

🔹 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: On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09008
• PDF: https://arxiv.org/pdf/2510.09008
• Project Page: https://keenyjin.github.io/epistemic/
• Github: https://github.com/joohoonlee/Epistemic

🔹 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: CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11718
• PDF: https://arxiv.org/pdf/2510.11718
• Project Page: https://math-vr.github.io/
• Github: https://github.com/HKU-MMLab/Math-VR-CodePlot-CoT

🔹 Datasets citing this paper:
https://huggingface.co/datasets/gogoduan/Math-VR-bench
https://huggingface.co/datasets/gogoduan/Math-VR-train

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11498
• PDF: https://arxiv.org/pdf/2510.11498
• Project Page: https://artifactsbenchmark.github.io/
• Github: https://github.com/Tencent-Hunyuan/ArtifactsBenchmark

🔹 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: RLFR: Extending Reinforcement Learning for LLMs with Flow Environment

🔹 Publication Date: Published on Oct 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.10201
• PDF: https://arxiv.org/pdf/2510.10201
• Project Page: https://jinghaoleven.github.io/RLFR/
• Github: https://github.com/Jinghaoleven/RLFR

🔹 Datasets citing this paper:
https://huggingface.co/datasets/JingHaoZ/RLFR-Dataset-LM
https://huggingface.co/datasets/JingHaoZ/RLFR-Dataset-VLM

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: InfiniHuman: Infinite 3D Human Creation with Precise Control

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11650
• PDF: https://arxiv.org/pdf/2510.11650
• Project Page: https://yuxuan-xue.com/infini-human

🔹 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