🔹 Title: Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification

🔹 Publication Date: Published on Sep 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.23061
• PDF: https://arxiv.org/pdf/2509.23061
• Project Page: https://DafnyComp.github.io/
• Github: https://DafnyComp.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: BPMN Assistant: An LLM-Based Approach to Business Process Modeling

🔹 Publication Date: Published on Sep 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.24592
• PDF: https://arxiv.org/pdf/2509.24592
• Github: https://github.com/jtlicardo/bpmn-assistant

🔹 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: Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models

🔹 Publication Date: Published on Sep 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.23233
• PDF: https://arxiv.org/pdf/2509.23233
• Github: https://github.com/stanford-oval/inconsistency-detection

🔹 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

Please help me collect a donation for an urgent and very necessary matter.

The amount is $300

I hope everyone will help me

PayPal:
https://www.paypal.me/HusseinSheikho

Usdt TRC-20 Address:
TMzAr8AFcZ1n5RXZa3BHPXHBRqugx9Skr7

Thanks

🔹 Title: Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play

🔹 Publication Date: Published on Sep 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.25541
• PDF: https://arxiv.org/pdf/2509.25541
• Github: https://github.com/wangqinsi1/Vision-Zero

🔹 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: TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.25760
• PDF: https://arxiv.org/pdf/2509.25760

🔹 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: OceanGym: A Benchmark Environment for Underwater Embodied Agents

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.26536
• PDF: https://arxiv.org/pdf/2509.26536
• Project Page: https://oceangpt.github.io/OceanGym/
• Github: https://github.com/OceanGPT/OceanGym

🔹 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: DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder

🔹 Publication Date: Published on Sep 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.25182
• PDF: https://arxiv.org/pdf/2509.25182

🔹 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: Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.26625
• PDF: https://arxiv.org/pdf/2509.26625
• Project Page: https://junlinhan.github.io/projects/lsbs/

🔹 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: Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.25758
• PDF: https://arxiv.org/pdf/2509.25758

🔹 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: Who's Your Judge? On the Detectability of LLM-Generated Judgments

🔹 Publication Date: Published on Sep 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.25154
• PDF: https://arxiv.org/pdf/2509.25154
• Github: https://llm-as-a-judge.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: MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use

🔹 Publication Date: Published on Sep 28

🔹 Paper Links:
• arXiv Page: https://arxiv.org/pdf/2509.24002
• PDF: https://arxiv.org/pdf/2509.24002
• Project Page: https://mcpmark.ai/
• Github: https://github.com/eval-sys/mcpmark

🔹 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: VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.26490
• PDF: https://arxiv.org/pdf/2509.26490
• Project Page: https://vitabench.github.io/
• Github: https://vitabench.github.io/

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/meituan/VitaBench

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

🔹 Title: dParallel: Learnable Parallel Decoding for dLLMs

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/pdf/2509.26488
• PDF: https://arxiv.org/pdf/2509.26488
• Github: https://github.com/czg1225/dParallel

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/Zigeng/dParallel_LLaDA_Distill_Data

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

🔹 Title: IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.26231
• PDF: https://arxiv.org/pdf/2509.26231
• Github: https://github.com/SHI-Labs/IMG-Multimodal-Diffusion-Alignment

🔹 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: Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention

🔹 Publication Date: Published on Sep 28

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.23610
• PDF: https://arxiv.org/pdf/2509.23610
• Project Page: https://cslikai.cn/Dolphin
• Github: https://github.com/JusperLee/Dolphin

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
• https://huggingface.co/spaces/JusperLee/Dolphin
==================================

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

🔹 Title: MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.26391
• PDF: https://arxiv.org/pdf/2509.26391
• Github: https://github.com/MCG-NJU/MotionRAG

🔹 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: Mem-α: Learning Memory Construction via Reinforcement Learning

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.25911
• PDF: https://arxiv.org/pdf/2509.25911

🔹 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: Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs

🔹 Publication Date: Published on Sep 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.22646
• PDF: https://arxiv.org/pdf/2509.22646
• Project Page: https://deeptracereward.github.io/
• Github: https://deeptracereward.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: Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.26628
• PDF: https://arxiv.org/pdf/2509.26628

🔹 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: OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!

🔹 Publication Date: Published on Sep 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.26495
• PDF: https://arxiv.org/pdf/2509.26495

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/declare-lab/OffTopicEval

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT