ML Research Hub
32.8K subscribers
4.38K photos
270 videos
23 files
4.74K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
πŸ”Ή Title: CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving

πŸ”Ή Publication Date: Published on Oct 14

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.12560
β€’ PDF: https://arxiv.org/pdf/2510.12560
β€’ Project Page: https://seu-zxj.github.io/CoIRL-AD/
β€’ Github: https://github.com/SEU-zxj/CoIRL-AD

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training

πŸ”Ή Publication Date: Published on Oct 12

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.12831
β€’ PDF: https://arxiv.org/pdf/2510.12831
β€’ Github: https://github.com/taichengguo/MTSQL-R1

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication

πŸ”Ή Publication Date: Published on Oct 12

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.10611
β€’ PDF: https://arxiv.org/pdf/2510.10611

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search

πŸ”Ή Publication Date: Published on Oct 12

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.10581
β€’ PDF: https://arxiv.org/pdf/2510.10581

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

πŸ”Ή Publication Date: Published on Oct 15

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.13778
β€’ PDF: https://arxiv.org/pdf/2510.13778
β€’ Project Page: https://internrobotics.github.io/internvla-m1.github.io/
β€’ Github: https://github.com/InternRobotics/InternVLA-M1

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark

πŸ”Ή Publication Date: Published on Oct 15

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.13759
β€’ PDF: https://arxiv.org/pdf/2510.13759

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models

πŸ”Ή Publication Date: Published on Oct 15

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.13626
β€’ PDF: https://arxiv.org/pdf/2510.13626
β€’ Project Page: https://sylvestf.github.io/LIBERO-plus/
β€’ Github: https://github.com/sylvestf/LIBERO-plus

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE

πŸ”Ή Publication Date: Published on Oct 15

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.13344
β€’ PDF: https://arxiv.org/pdf/2510.13344
β€’ Github: https://github.com/HITsz-TMG/Uni-MoE/blob/master/UniMoE-Audio

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Direct Multi-Token Decoding

πŸ”Ή Publication Date: Published on Oct 13

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.11958
β€’ PDF: https://arxiv.org/pdf/2510.11958

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

πŸ”Ή Publication Date: Published on Oct 15

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.13554
β€’ PDF: https://arxiv.org/pdf/2510.13554

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model

πŸ”Ή Publication Date: Published on Oct 13

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.10921
β€’ PDF: https://arxiv.org/pdf/2510.10921
β€’ Project Page: https://360cvgroup.github.io/FG-CLIP/

πŸ”Ή Datasets citing this paper:
β€’ https://huggingface.co/datasets/qihoo360/DCI-CN
β€’ https://huggingface.co/datasets/qihoo360/BoxClass-CN
β€’ https://huggingface.co/datasets/qihoo360/LIT-CN
β€’ https://huggingface.co/datasets/qihoo360/DOCCI-CN

πŸ”Ή Spaces citing this paper:
β€’ https://huggingface.co/spaces/qihoo360/FG-CLIP2-Retrieval-demo
β€’ https://huggingface.co/spaces/qihoo360/FG-CLIP2-Densefeature-demo
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

πŸ”Ή Publication Date: Published on Oct 11

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.10274
β€’ PDF: https://arxiv.org/pdf/2510.10274
β€’ Project Page: https://thu-air-dream.github.io/X-VLA/
β€’ Github: https://github.com/2toinf/X-VLA.git

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Universal Image Restoration Pre-training via Masked Degradation Classification

πŸ”Ή Publication Date: Published on Oct 15

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.13282
β€’ PDF: https://arxiv.org/pdf/2510.13282
β€’ Project Page: https://github.com/MILab-PKU/MaskDCPT
β€’ Github: https://github.com/MILab-PKU/MaskDCPT

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
❀1
Contribute with us to expand the services offered in our channel

We plan to use an advanced AI model to add more information about the most prominent events, models, and articles released and provide explanations.

This requires preparing an infrastructure for our server and purchasing an API for an AI model.

Contribute to the development of our community with us

Contact me @husseinsheikho
ML Research Hub pinned Β«Contribute with us to expand the services offered in our channel We plan to use an advanced AI model to add more information about the most prominent events, models, and articles released and provide explanations. This requires preparing an infrastructure…»
πŸ”Ή Title: Stronger Together: On-Policy Reinforcement Learning for Collaborative LLMs

πŸ”Ή Publication Date: Published on Oct 13

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.11062
β€’ PDF: https://arxiv.org/pdf/2510.11062
β€’ Project Page: https://pettingllms-ai.github.io/
β€’ Github: https://github.com/pettingllms-ai/PettingLLMs

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Reasoning in Space via Grounding in the World

πŸ”Ή Publication Date: Published on Oct 15

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.13800
β€’ PDF: https://arxiv.org/pdf/2510.13800
β€’ Project Page: https://yiming-cc.github.io/gs-reasoner/
β€’ Github: https://github.com/WU-CVGL/GS-Reasoner

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain

πŸ”Ή Publication Date: Published on Oct 15

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.13255
β€’ PDF: https://arxiv.org/pdf/2510.13255
β€’ Github: https://github.com/LilTiger/HFTP

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model

πŸ”Ή Publication Date: Published on Oct 13

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.11653
β€’ PDF: https://arxiv.org/pdf/2510.11653

πŸ”Ή Datasets citing this paper:
β€’ https://huggingface.co/datasets/brendel-group/MATH-Beyond

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: EAGER: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling

πŸ”Ή Publication Date: Published on Oct 13

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.11170
β€’ PDF: https://arxiv.org/pdf/2510.11170

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: The Art of Scaling Reinforcement Learning Compute for LLMs

πŸ”Ή Publication Date: Published on Oct 15

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.13786
β€’ PDF: https://arxiv.org/pdf/2510.13786

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT