🔹 Title: Understanding Tool-Integrated Reasoning

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19201
• PDF: https://arxiv.org/pdf/2508.19201
• Project Page: https://zhongwenxu.notion.site/Understanding-Tool-Integrated-Reasoning-2551c4e140e3805489fadcc802a1ea83

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Spacer: Towards Engineered Scientific Inspiration

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17661
• PDF: https://arxiv.org/pdf/2508.17661
• Github: https://github.com/asteromorph-corp/spacer

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19247
• PDF: https://arxiv.org/pdf/2508.19247
• Project Page: https://huanngzh.github.io/VoxHammer-Page/
• Github: https://github.com/Nelipot-Lee/VoxHammer/Edit3D-Bench

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/huanngzh/Edit3D-Bench

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

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

🔹 Title: Unraveling the cognitive patterns of Large Language Models through module communities

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18192
• PDF: https://arxiv.org/pdf/2508.18192

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19209
• PDF: https://arxiv.org/pdf/2508.19209
• Project Page: https://omnihuman-lab.github.io/v1_5/

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18756
• PDF: https://arxiv.org/pdf/2508.18756
• Github: https://github.com/ZihaoHuang-notabot/Ultra-Sparse-Memory-Network

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18124
• PDF: https://arxiv.org/pdf/2508.18124
• Github: https://github.com/CMPhysBench/CMPhysBench%5D

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

🔹 Publication Date: Published on Aug 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17445
• PDF: https://arxiv.org/pdf/2508.17445

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Wan-S2V: Audio-Driven Cinematic Video Generation

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18621
• PDF: https://arxiv.org/pdf/2508.18621

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting

🔹 Publication Date: Published on Aug 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.16697
• PDF: https://arxiv.org/pdf/2508.16697

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2502.18080
• PDF: https://arxiv.org/pdf/2508.18773

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.00910
• PDF: https://arxiv.org/pdf/2508.18370

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: FastMesh:Efficient Artistic Mesh Generation via Component Decoupling

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19188
• PDF: https://arxiv.org/pdf/2508.19188
• Project Page: https://jhkim0759.github.io/projects/FastMesh/

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Evaluating, Synthesizing, and Enhancing for Customer Support Conversation

🔹 Publication Date: Published on Aug 6

🔹 Abstract: A structured framework and datasets for training customer service agents using well-defined support strategies improve the quality of customer support interactions and problem resolution. AI-generated summary Effective customer support requires not only accurate problem solving but also structured and empathetic communication aligned with professional standards. However, existing dialogue datasets often lack strategic guidance, and real-world service data is difficult to access and annotate. To address this, we introduce the task of Customer Support Conversation (CSC), aimed at training customer service agents to respond using well-defined support strategies. We propose a structured CSC framework grounded in COPC guidelines , defining five conversational stages and twelve strategies to guide high-quality interactions. Based on this, we construct CSConv , an evaluation dataset of 1,855 real-world customer-agent conversations rewritten using LLMs to reflect deliberate strategy use, and annotated accordingly. Additionally, we develop a role-playing approach that simulates strategy-rich conversations using LLM-powered roles aligned with the CSC framework, resulting in the training dataset RoleCS . Experiments show that fine-tuning strong LLMs on RoleCS significantly improves their ability to generate high-quality, strategy-aligned responses on CSConv . Human evaluations further confirm gains in problem resolution. All code and data will be made publicly available at https://github.com/aliyun/qwen-dianjin.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.04423

• PDF: https://arxiv.org/pdf/2508.04423

• Github: https://github.com/aliyun/qwen-dianjin

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Autoregressive Universal Video Segmentation Model

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19242
• PDF: https://arxiv.org/pdf/2508.19242

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: MovieCORE: COgnitive REasoning in Movies

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19026
• PDF: https://arxiv.org/pdf/2508.19026
• Github: https://joslefaure.github.io/assets/html/moviecore.html

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18271
• PDF: https://arxiv.org/pdf/2508.18271
• Project Page: https://objfiller3d.github.io/
• Github: https://github.com/objfiller3d/ObjFiller-3D

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18672
• PDF: https://arxiv.org/pdf/2508.18672
• Github: https://github.com/

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: Sotopia-RL: Reward Design for Social Intelligence

🔹 Publication Date: Published on Aug 5

🔹 Abstract: Sotopia-RL, a novel reinforcement learning framework, enhances social intelligence in large language models by refining feedback into utterance-level, multi-dimensional rewards, improving performance in social tasks. AI-generated summary Social intelligence has become a critical capability for large language models (LLMs), enabling them to engage effectively in real-world social tasks such as accommodation, persuasion, collaboration, and negotiation. Reinforcement learning (RL) is a natural fit for training socially intelligent agents because it allows models to learn sophisticated strategies directly through social interactions. However, social interactions have two key characteristics that set barriers for RL training: (1) partial observability , where utterances have indirect and delayed effects that complicate credit assignment, and (2) multi-dimensionality , where behaviors such as rapport-building or knowledge-seeking contribute indirectly to goal achievement. These characteristics make Markov decision process (MDP)-based RL with single-dimensional episode-level rewards inefficient and unstable. To address these challenges, we propose Sotopia-RL , a novel framework that refines coarse episode-level feedback into utterance-level, multi-dimensional rewards . Utterance-level credit assignment mitigates partial observability by attributing outcomes to individual utterances, while multi-dimensional rewards capture the full richness of social interactions and reduce reward hacking . Experiments in Sotopia , an open-ended social learning environment, demonstrate that Sotopia-RL achieves state-of-the-art social goal completion scores (7.17 on Sotopia -hard and 8.31 on Sotopia -full), significantly outperforming existing approaches. Ablation studies confirm the necessity of both utterance-level credit assignment and multi-dimensional reward design for RL training. Our implementation is publicly available at: https://github.com/ sotopia -lab/ sotopia-rl .

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.03905

• PDF: https://arxiv.org/pdf/2508.03905

• Github: https://github.com/sotopia-lab/sotopia-rl

🔹 Datasets citing this paper:
No datasets found

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

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

🔹 Title: NeRF Is a Valuable Assistant for 3D Gaussian Splatting

🔹 Publication Date: Published on Jul 31

🔹 Abstract: NeRF-GS combines Neural Radiance Fields and 3D Gaussian Splatting to enhance 3D scene representation and performance through joint optimization and shared spatial information. AI-generated summary We introduce NeRF-GS, a novel framework that jointly optimizes Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). This framework leverages the inherent continuous spatial representation of NeRF to mitigate several limitations of 3DGS, including sensitivity to Gaussian initialization , limited spatial awareness , and weak inter-Gaussian correlations , thereby enhancing its performance. In NeRF-GS, we revisit the design of 3DGS and progressively align its spatial features with NeRF, enabling both representations to be optimized within the same scene through shared 3D spatial information. We further address the formal distinctions between the two approaches by optimizing residual vectors for both implicit features and Gaussian positions to enhance the personalized capabilities of 3DGS. Experimental results on benchmark datasets show that NeRF-GS surpasses existing methods and achieves state-of-the-art performance. This outcome confirms that NeRF and 3DGS are complementary rather than competing, offering new insights into hybrid approaches that combine 3DGS and NeRF for efficient 3D scene representation.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2507.23374

• PDF: https://arxiv.org/pdf/2507.23374

🔹 Datasets citing this paper:
No datasets found

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

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