🔹 Title: AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09889
• PDF: https://arxiv.org/pdf/2508.09889

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery

🔹 Publication Date: Published on Aug 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.08401
• PDF: https://arxiv.org/pdf/2508.08401

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

🔹 Publication Date: Published on Aug 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.06009
• PDF: https://arxiv.org/pdf/2508.06009
• Github: https://github.com/junfeng0288/MathReal

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/junfeng0288/MathReal

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

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

🔹 Title: IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09456
• PDF: https://arxiv.org/pdf/2508.09456

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

🔹 Publication Date: Published on Aug 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.05613
• PDF: https://arxiv.org/pdf/2508.05613
• Project Page: https://zju-real.github.io/cooper/
• Github: https://github.com/ZJU-REAL/cooper

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09987
• PDF: https://arxiv.org/pdf/2508.09987
• Project Page: https://yejy53.github.io/Echo-4o/
• Github: https://yejy53.github.io/Echo-4o

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09968
• PDF: https://arxiv.org/pdf/2508.09968
• Github: https://noisehypernetworks.github.io/

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

🔹 Publication Date: Published on Aug 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09192
• PDF: https://arxiv.org/pdf/2508.09192
• Project Page: https://zhijie-group.github.io/Discrete-Diffusion-Forcing/
• Github: https://zhijie-group.github.io/Discrete-Diffusion-Forcing/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
• https://huggingface.co/spaces/zhijie3/D2F-LLaDA-Instruct-8B
==================================

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

🔹 Title: Story2Board: A Training-Free Approach for Expressive Storyboard Generation

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09983
• PDF: https://arxiv.org/pdf/2508.09983
• Project Page: https://daviddinkevich.github.io/Story2Board/
• Github: https://github.com/daviddinkevich/Story2Board

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

🔹 Publication Date: Published on Aug 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.07901
• PDF: https://arxiv.org/pdf/2508.07901
• Github: https://stand-in-video.github.io/

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09736
• PDF: https://arxiv.org/pdf/2508.09736
• Project Page: https://m3-agent.github.io/
• Github: https://github.com/ByteDance-Seed/m3-agent

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/ByteDance-Seed/M3-Bench

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

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

🔹 Title: Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09776
• PDF: https://arxiv.org/pdf/2508.09776

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

🔹 Publication Date: Published on Aug 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.07750
• PDF: https://arxiv.org/pdf/2508.07750

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09945
• PDF: https://arxiv.org/pdf/2508.09945
• Github: https://github.com/JackLingjie/VisCodex

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

🔹 Publication Date: Published on Aug 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.06944
• PDF: https://arxiv.org/pdf/2508.06944
• Github: https://github.com/TSYJ-He/AMFT

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

🔹 Publication Date: Published on Aug 3

🔹 Abstract: LiveMCPBench provides a comprehensive benchmark for evaluating LLM agents across a diverse set of real-world tasks in the MCP ecosystem, using a scalable evaluation pipeline and adaptive judging framework. AI-generated summary With the rapid development of Model Context Protocol ( MCP ), the number of MCP servers has surpassed 10,000. However, existing MCP benchmarks are limited to single-server settings with only a few tools, hindering effective evaluation of agent capabilities in large-scale, real-world scenarios. To address this limitation, we present LiveMCPBench , the first comprehensive benchmark comprising 95 real-world tasks grounded in the MCP ecosystem, designed to evaluate LLM agents at scale across diverse servers. To support a scalable and reproducible evaluation pipeline in large-scale MCP environments, we curate LiveMCPTool , a diverse and readily deployable collection of 70 MCP servers and 527 tools. Furthermore, we introduce LiveMCPEval , an LLM-as-a-Judge framework that enables automated and adaptive evaluation in dynamic, time-varying task environments, achieving 81% agreement with human reviewers . Finally, we propose the MCP Copilot Agent , a multi-step agent that routes tools for dynamic planning and executes tools for API interaction across the entire LiveMCPTool suite. Our evaluation covers 10 leading models, with the best-performing model (Claude-Sonnet-4) reaching a 78.95% success rate. However, we observe large performance variance across models, and several widely-used models perform poorly in LiveMCPBench 's complex, tool-rich environments. Overall, LiveMCPBench offers the first unified framework for benchmarking LLM agents in realistic, tool-rich, and dynamic MCP environments, laying a solid foundation for scalable and reproducible research on agent capabilities. Our code and data will be publicly available at https://icip-cas.github.io/ LiveMCPBench .

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.01780

• PDF: https://arxiv.org/pdf/2508.01780

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/ICIP/LiveMCPBench

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

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

🔹 Title: GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09667
• PDF: https://arxiv.org/pdf/2508.09667

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing

🔹 Publication Date: Published on Aug 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.06937
• PDF: https://arxiv.org/pdf/2508.06937
• Project Page: https://vaynexie.github.io/CannyEdit/
• Github: https://github.com/vaynexie/CannyEdit/tree/main

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Decentralized Aerial Manipulation of a Cable-Suspended Load using Multi-Agent Reinforcement Learning

🔹 Publication Date: Published on Aug 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.01522
• PDF: https://arxiv.org/pdf/2508.01522
• Project Page: https://autonomousrobots.nl/paper_websites/aerial-manipulation-marl
• Github: https://github.com/Aerial-Manipulation-Lab/MARL_cooperative_aerial_manipulation_ext

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: ASM-UNet: Adaptive Scan Mamba Integrating Group Commonalities and Individual Variations for Fine-Grained Segmentation

🔹 Publication Date: Published on Aug 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.07237
• PDF: https://arxiv.org/pdf/2508.07237
• Github: https://github.com/YqunYang/ASM-UNet

🔹 Datasets citing this paper:
No datasets found

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

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