🔹 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://news.1rj.ru/str/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://news.1rj.ru/str/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://news.1rj.ru/str/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://news.1rj.ru/str/DataScienceT

🔹 Title: ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.15804
• PDF: https://arxiv.org/pdf/2508.15804

🔹 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: Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/pdf/2508.19202v1
• PDF: https://arxiv.org/pdf/2508.19202

🔹 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: ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation

🔹 Publication Date: Published on Aug 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17234
• PDF: https://arxiv.org/pdf/2508.17234

🔹 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: DrugReasoner: Interpretable Drug Approval Prediction with a Reasoning-augmented Language Model

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18579
• PDF: https://arxiv.org/pdf/2508.18579
• Github: https://github.com/mohammad-gh009/DrugReasoner

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/Moreza009/drug_approval_prediction

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

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

🔹 Title: Steering When Necessary: Flexible Steering Large Language Models with Backtracking

🔹 Publication Date: Published on Aug 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.17621
• PDF: https://arxiv.org/pdf/2508.17621
• Github: https://github.com/gjw185/FASB

🔹 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: Forecasting Probability Distributions of Financial Returns with Deep Neural Networks

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.18921
• PDF: https://arxiv.org/pdf/2508.18921
• Github: https://github.com/jmichankow/deep_learning_probability

🔹 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: Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering

🔹 Publication Date: Published on Aug 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.15213
• PDF: https://arxiv.org/pdf/2508.15213

🔹 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

What do you think of the services offered my Bot??

nice 👍

It's okay 👎

🔹 Title: Self-Rewarding Vision-Language Model via Reasoning Decomposition

🔹 Publication Date: Published on Aug 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19652
• PDF: https://arxiv.org/pdf/2508.19652

🔹 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: Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents

🔹 Publication Date: Published on Aug 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19493
• PDF: https://arxiv.org/pdf/2508.19493
• Project Page: https://zhixin-l.github.io/SAPA-Bench
• Github: https://github.com/Zhixin-L/SAPA-Bench

🔹 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: CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning

🔹 Publication Date: Published on Aug 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.20096
• PDF: https://arxiv.org/pdf/2508.20096
• Project Page: https://github.com/OpenIXCLab/CODA
• Github: https://github.com/OpenIXCLab/CODA

🔹 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: StepWiser: Stepwise Generative Judges for Wiser Reasoning

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: http://arxiv.org/abs/2508.19229
• PDF: https://arxiv.org/pdf/2508.19229

🔹 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: AudioStory: Generating Long-Form Narrative Audio with Large Language Models

🔹 Publication Date: Published on Aug 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.20088
• PDF: https://arxiv.org/pdf/2508.20088

🔹 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: Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

🔹 Publication Date: Published on Aug 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.20072
• PDF: https://arxiv.org/pdf/2508.20072

🔹 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: Predicting the Order of Upcoming Tokens Improves Language Modeling

🔹 Publication Date: Published on Aug 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19228
• PDF: https://arxiv.org/pdf/2508.19228
• Github: https://github.com/zaydzuhri/token-order-prediction

🔹 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: IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

🔹 Publication Date: Published on Aug 1

🔹 Abstract: IGL-Nav uses an incremental 3D Gaussian representation for efficient and accurate image-goal navigation in 3D space, outperforming existing methods and applicable in real-world settings. AI-generated summary Visual navigation with an image as goal is a fundamental and challenging problem. Conventional methods either rely on end-to-end RL learning or modular-based policy with topological graph or BEV map as memory, which cannot fully model the geometric relationship between the explored 3D environment and the goal image. In order to efficiently and accurately localize the goal image in 3D space, we build our navigation system upon the renderable 3D gaussian ( 3DGS ) representation. However, due to the computational intensity of 3DGS optimization and the large search space of 6-DoF camera pose , directly leveraging 3DGS for image localization during agent exploration process is prohibitively inefficient. To this end, we propose IGL-Nav , an Incremental 3D Gaussian Localization framework for efficient and 3D-aware image-goal navigation. Specifically, we incrementally update the scene representation as new images arrive with feed-forward monocular prediction . Then we coarsely localize the goal by leveraging the geometric information for discrete space matching, which can be equivalent to efficient 3D convolution. When the agent is close to the goal, we finally solve the fine target pose with optimization via differentiable rendering . The proposed IGL-Nav outperforms existing state-of-the-art methods by a large margin across diverse experimental configurations. It can also handle the more challenging free-view image-goal setting and be deployed on real-world robotic platform using a cellphone to capture goal image at arbitrary pose. Project page: https://gwxuan.github.io/ IGL-Nav /.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.00823

• PDF: https://arxiv.org/pdf/2508.00823

• Project Page: https://gwxuan.github.io/IGL-Nav/

• Github: https://gwxuan.github.io/IGL-Nav/

🔹 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: Diffusion Language Models Know the Answer Before Decoding

🔹 Publication Date: Published on Aug 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.19982
• PDF: https://arxiv.org/pdf/2508.19982

🔹 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