ML Research Hub – Telegram
ML Research Hub
32.8K subscribers
4.43K photos
272 videos
23 files
4.78K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
🔹 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
🔹 Title: RePro: Training Language Models to Faithfully Recycle the Web for Pretraining

🔹 Publication Date: Published on Oct 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.10681
• PDF: https://arxiv.org/pdf/2510.10681
• Github: https://github.com/cxcscmu/RePro

🔹 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: Are Large Reasoning Models Interruptible?

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11713
• PDF: https://arxiv.org/pdf/2510.11713
• Project Page: https://dynamic-lm.github.io/

🔹 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: IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11647
• PDF: https://arxiv.org/pdf/2510.11647
• Project Page: https://ryanchenyn.github.io/projects/IVEBench/

🔹 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: LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11512
• PDF: https://arxiv.org/pdf/2510.11512

🔹 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: Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09781
• PDF: https://arxiv.org/pdf/2510.09781
• Github: https://github.com/HowieHwong/Agentic-Guardian

🔹 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: BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

🔹 Publication Date: Published on Oct 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.10666
• PDF: https://arxiv.org/pdf/2510.10666
• Project Page: https://tiger-ai-lab.github.io/BrowserAgent/
• Github: https://github.com/TIGER-AI-Lab/BrowserAgent

🔹 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: High-Fidelity Simulated Data Generation for Real-World Zero-Shot Robotic Manipulation Learning with Gaussian Splatting

🔹 Publication Date: Published on Oct 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.10637
• PDF: https://arxiv.org/pdf/2510.10637
• Project Page: https://robosimgs.github.io/

🔹 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 Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution

🔹 Publication Date: Published on Oct 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.10493
• PDF: https://arxiv.org/pdf/2510.10493
• Project Page: https://github.com/LLM-NodeJS-dataset
• Github: https://github.com/LLM-NodeJS-dataset/LLM-NodeJS-dataset

🔹 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: Don't Just Fine-tune the Agent, Tune the Environment

🔹 Publication Date: Published on Oct 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.10197
• PDF: https://arxiv.org/pdf/2510.10197

🔹 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: VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing

🔹 Publication Date: Published on Oct 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.05213
• PDF: https://arxiv.org/pdf/2510.05213
• Project Page: https://yixiaowang7.github.io/ver_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
🔹 Title: HUME: Measuring the Human-Model Performance Gap in Text Embedding Task

🔹 Publication Date: Published on Oct 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.10062
• PDF: https://arxiv.org/pdf/2510.10062

🔹 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
🔹 Title: Spotlight on Token Perception for Multimodal Reinforcement Learning

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09285
• PDF: https://arxiv.org/pdf/2510.09285
• Project Page: https://huggingface.co/collections/chamber111/vppo-data-68e7aaafe1bffbab844d341b
• Github: https://github.com/huaixuheqing/VPPO-RL

🔹 Datasets citing this paper:
https://huggingface.co/datasets/chamber111/VPPO-Eval
https://huggingface.co/datasets/chamber111/VPPO_ViRL39K_train
https://huggingface.co/datasets/chamber111/VPPO_MMK12_validation

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

For more data science resources:
https://news.1rj.ru/str/DataScienceT
🔹 Title: ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11652
• PDF: https://arxiv.org/pdf/2510.11652

🔹 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: InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11341
• PDF: https://arxiv.org/pdf/2510.11341
• Project Page: https://hmwang2002.github.io/release/internnoscript/
• Github: https://github.com/hmwang2002/InternSVG

🔹 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: From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07624
• PDF: https://arxiv.org/pdf/2510.07624
• Github: https://github.com/abenechehab/nll_to_po

🔹 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 Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11052
• PDF: https://arxiv.org/pdf/2510.11052

🔹 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: CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs

🔹 Publication Date: Published on Oct 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.09871
• PDF: https://arxiv.org/pdf/2510.09871
• Project Page: https://github.com/nafisenik/CoBia
• Github: https://github.com/nafisenik/CoBia

🔹 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: Through the Perspective of LiDAR: A Feature-Enriched and Uncertainty-Aware Annotation Pipeline for Terrestrial Point Cloud Segmentation

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06582
• PDF: https://arxiv.org/pdf/2510.06582
• Project Page: https://fz-rit.github.io/through-the-lidars-eye/

🔹 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 Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers

🔹 Publication Date: Published on Oct 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.11218
• PDF: https://arxiv.org/pdf/2510.11218
• Github: https://github.com/WorldHellow/SLAQ

🔹 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