🔹 Title: Pruning Overparameterized Multi-Task Networks for Degraded Web Image Restoration

🔹 Publication Date: Published on Oct 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.14463
• PDF: https://arxiv.org/pdf/2510.14463
• Github: https://github.com/Thomkat/MIR-L

🔹 Datasets citing this paper:
No datasets found

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

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

🤖🧠 Unlocking Creativity with Awesome ChatGPT Prompts: The Ultimate Guide for AI Enthusiasts

🗓️ 22 Oct 2025
📚 AI News & Trends

Artificial Intelligence has transformed how we create, communicate, and innovate and at the heart of this revolution lies prompt engineering. One of the most powerful tools in this domain is the “Awesome ChatGPT Prompts” repository – a growing collection of creative, technical and professional prompts designed for ChatGPT and other large language models like Claude, ...

#ChatGPT #PromptEngineering #AIEnthusiasts #ArtificialIntelligence #LargeLanguageModels #AICreativity

🤖🧠 AgentFly: The Future of Reinforcement Learning for Intelligent Language Model Agents

🗓️ 22 Oct 2025
📚 AI News & Trends

AgentFly is a cutting-edge framework developed by researchers at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) to revolutionize how large language models (LLMs) learn and act. It combines the power of reinforcement learning (RL) with language model agents enabling them to go beyond static prompt responses and learn through real-time feedback and experience. ...

#ReinforcementLearning #LLMs #LanguageModelAgents #ArtificialIntelligence #AgentFly #AIFramework

🤖🧠 OpenSearch for AI Agents: Empowering Intelligent Search and Automation

🗓️ 22 Oct 2025
📚 AI News & Trends

As artificial intelligence (AI) continues to evolve, one of the most transformative shifts has been the rise of AI agents – autonomous systems capable of reasoning, interacting, and performing complex tasks. From customer support chatbots to autonomous data analysts, these agents rely heavily on efficient data retrieval mechanisms. However, traditional search systems often struggle to ...

#OpenSearch #AIAgents #IntelligentSearch #AIautomation #ArtificialIntelligence #DataRetrieval

🔹 Title: LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19363
• PDF: https://arxiv.org/pdf/2510.19363

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19336
• PDF: https://arxiv.org/pdf/2510.19336

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: olmOCR 2: Unit Test Rewards for Document OCR

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19817
• PDF: https://arxiv.org/pdf/2510.19817
• Project Page: https://olmocr.allen.ai/
• Github: https://github.com/allenai/olmocr

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19808
• PDF: https://arxiv.org/pdf/2510.19808

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19488
• PDF: https://arxiv.org/pdf/2510.19488
• Project Page: https://videoagenttrek.github.io/
• Github: https://github.com/xlang-ai/VideoAgentTrek

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: TheMCPCompany: Creating General-purpose Agents with Task-specific Tools

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19286
• PDF: https://arxiv.org/pdf/2510.19286
• Github: https://github.com/Reza-esfandiarpoor/the-mcp-company

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19338
• PDF: https://arxiv.org/pdf/2510.19338

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: ColorAgent: Building A Robust, Personalized, and Interactive OS Agent

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19386
• PDF: https://arxiv.org/pdf/2510.19386
• Github: https://github.com/MadeAgents/mobile-use

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Unified Reinforcement and Imitation Learning for Vision-Language Models

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19307
• PDF: https://arxiv.org/pdf/2510.19307
• Project Page: https://byungkwanlee.github.io/RIL-page/
• Github: https://byungkwanlee.github.io/RIL-page/

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19457
• PDF: https://arxiv.org/pdf/2510.19457
• Project Page: https://mined-lmm.github.io/

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints

🔹 Publication Date: Published on Oct 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.19316
• PDF: https://arxiv.org/pdf/2510.19316
• Project Page: https://kore-lmm.github.io/

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: FinSight: Towards Real-World Financial Deep Research

🔹 Publication Date: Published on Oct 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.16844
• PDF: https://arxiv.org/pdf/2510.16844

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18428
• PDF: https://arxiv.org/pdf/2510.18428

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18927
• PDF: https://arxiv.org/pdf/2510.18927
• Project Page: https://github.com/WooooDyy/BAPO
• Github: https://github.com/WooooDyy/BAPO

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18941
• PDF: https://arxiv.org/pdf/2510.18941

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/nvidia/ProfBench

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

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

🔹 Title: NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18940
• PDF: https://arxiv.org/pdf/2510.18940
• Github: https://github.com/FightingFighting/NeuroAda.git

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: RIR-Mega: a large-scale simulated room impulse response dataset for machine learning and room acoustics modeling

🔹 Publication Date: Published on Oct 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.18917
• PDF: https://arxiv.org/pdf/2510.18917
• Project Page: https://doi.org/10.5281/zenodo.17387402
• Github: https://github.com/mandip42/rirmega

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/mandipgoswami/rirmega

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

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