ML Research Hub
32.8K subscribers
4.36K photos
267 videos
23 files
4.71K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
🔹 Title: The Markovian Thinker

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06557
• PDF: https://arxiv.org/pdf/2510.06557
• Github: https://github.com/McGill-NLP/the-markovian-thinker

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: Revisiting the Uniform Information Density Hypothesis in LLM Reasoning Traces

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06953
• PDF: https://arxiv.org/pdf/2510.06953

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought

🔹 Publication Date: Published on Oct 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.04230
• PDF: https://arxiv.org/pdf/2510.04230

🔹 Datasets citing this paper:
https://huggingface.co/datasets/KOREAson/YiSang-STEM_Code-Unfiltered
https://huggingface.co/datasets/KOREAson/YiSang-HighQuality
https://huggingface.co/datasets/KOREAson/YiSang-3.7M

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling

🔹 Publication Date: Published on Oct 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.04204
• PDF: https://arxiv.org/pdf/2510.04204

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles

🔹 Publication Date: Published on Oct 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06475
• PDF: https://arxiv.org/pdf/2510.06475

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering

🔹 Publication Date: Published on Oct 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06426
• PDF: https://arxiv.org/pdf/2510.06426

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: Glocal Information Bottleneck for Time Series Imputation

🔹 Publication Date: Published on Oct 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.04910
• PDF: https://arxiv.org/pdf/2510.04910
• Github: https://github.com/Muyiiiii/NeurIPS-25-Glocal-IB

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: A Single Character can Make or Break Your LLM Evals

🔹 Publication Date: Published on Oct 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.05152
• PDF: https://arxiv.org/pdf/2510.05152

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: Code Agent can be an End-to-end System Hacker: Benchmarking Real-world Threats of Computer-use Agent

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06607
• PDF: https://arxiv.org/pdf/2510.06607
• Project Page: https://eddyluo.com/AdvCUA/

🔹 Datasets citing this paper:
https://huggingface.co/datasets/MomoUchi/AdvCUA

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: Reinforcement Mid-Training

🔹 Publication Date: Published on Sep 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.24375
• PDF: https://arxiv.org/pdf/2509.24375
• Github: https://github.com/Mid-Training/RMT

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: M3Retrieve: Benchmarking Multimodal Retrieval for Medicine

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06888
• PDF: https://arxiv.org/pdf/2510.06888

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08565
• PDF: https://arxiv.org/pdf/2510.08565
• Project Page: https://internvl.github.io/blog/2025-10-10-NaViL/
• Github: https://github.com/OpenGVLab/NaViL

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: Agent Learning via Early Experience

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08558
• PDF: https://arxiv.org/pdf/2510.08558

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
1
🔹 Title: MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08540
• PDF: https://arxiv.org/pdf/2510.08540

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG

🔹 Publication Date: Published on Oct 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.03663
• PDF: https://arxiv.org/pdf/2510.03663
• Github: https://github.com/SalesforceAIResearch/UniDoc-Bench

🔹 Datasets citing this paper:
https://huggingface.co/datasets/Salesforce/UniDoc-Bench

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: DeepPrune: Parallel Scaling without Inter-trace Redundancy

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08483
• PDF: https://arxiv.org/pdf/2510.08483
• Project Page: https://deepprune.github.io/
• Github: https://github.com/THU-KEG/DeepPrune

🔹 Datasets citing this paper:
https://huggingface.co/datasets/THU-KEG/DeepPrune

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward

🔹 Publication Date: Published on Oct 3

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.03222
• PDF: https://arxiv.org/pdf/2510.03222
• Github: https://github.com/CarlanLark/Lp-Reg-dev

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08431
• PDF: https://arxiv.org/pdf/2510.08431
• Github: https://github.com/NVlabs/rcm

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: UniVideo: Unified Understanding, Generation, and Editing for Videos

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08377
• PDF: https://arxiv.org/pdf/2510.08377
• Project Page: https://congwei1230.github.io/UniVideo/

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
🔹 Title: First Try Matters: Revisiting the Role of Reflection in Reasoning Models

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08308
• PDF: https://arxiv.org/pdf/2510.08308

🔹 Datasets citing this paper:
No datasets found

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

For more data science resources:
https://t.me/DataScienceT
1
🔹 Title: NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07172
• PDF: https://arxiv.org/pdf/2510.07172
• Github: https://github.com/HKUST-KnowComp/NewtonBench

🔹 Datasets citing this paper:
No datasets found

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

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