🔹 Title: Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation

🔹 Publication Date: Published on Aug 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.12040
• PDF: https://arxiv.org/pdf/2508.12040

🔹 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: A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models

🔹 Publication Date: Published on Aug 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.12903
• PDF: https://arxiv.org/pdf/2508.12903

🔹 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: MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.13186
• PDF: https://arxiv.org/pdf/2508.13186
• Github: https://github.com/MMBrowseComp/MM-BrowseComp

🔹 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: CAMAR: Continuous Actions Multi-Agent Routing

🔹 Publication Date: Published on Aug 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.12845
• PDF: https://arxiv.org/pdf/2508.12845

🔹 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: Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward

🔹 Publication Date: Published on Aug 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.12800
• PDF: https://arxiv.org/pdf/2508.12800

🔹 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

🔥 $10.000 WITH LISA!

Lisa earned $200,000 in a month, and now it’s YOUR TURN!

She’s made trading SO SIMPLE that anyone can do it.

❗️Just copy her signals every day
❗️Follow her trades step by step
❗️Earn $1,000+ in your first week – GUARANTEED!

🚨 BONUS: Lisa is giving away $10,000 to her subscribers!

Don’t miss this once-in-a-lifetime opportunity. Free access for the first 500 people only!

👉 CLICK HERE TO JOIN NOW 👈

🔹 Title: Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

🔹 Publication Date: Published on Aug 1

🔹 Abstract: Foundation-Sec-8B-Instruct is a cybersecurity-focused LLM designed for chat-style interactions and instruction-following, outperforming other models in cybersecurity tasks while matching their instruction-following capabilities. AI-generated summary Large language models ( LLMs ) have shown remarkable success across many domains, yet their integration into cybersecurity applications remains limited due to a lack of general-purpose cybersecurity data, representational complexity, and safety and regulatory concerns. To address this gap, we previously introduced Foundation-Sec-8B , a cybersecurity -focused LLM suitable for fine-tuning on downstream tasks. That model, however, was not designed for chat-style interactions or instruction-following . In this report, we release Foundation-Sec-8B -Instruct: a model specifically trained for general-purpose cybersecurity dialogue . Built on Foundation-Sec-8B , it combines domain-specific knowledge with instruction-following , conversational capabilities , and alignment with human preferences to produce high-quality, relevant responses. Comprehensive evaluations show that Foundation-Sec-8B -Instruct outperforms Llama 3.1-8B-Instruct on a range of cybersecurity tasks while matching its instruction-following performance. It is also competitive with GPT-4o-mini on cyber threat intelligence and instruction-following tasks. We envision Foundation-Sec-8B -Instruct becoming an indispensable assistant in the daily workflows of cybersecurity professionals. We release the model publicly at https://huggingface.co/fdtn-ai/ Foundation-Sec-8B -Instruct.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.01059

• PDF: https://arxiv.org/pdf/2508.01059

🔹 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: Rapidly Adapting to New Voice Spoofing: Few-Shot Detection of Synthesized Speech Under Distribution Shifts

🔹 Publication Date: Published on Aug 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.13320
• PDF: https://arxiv.org/pdf/2508.13320

🔹 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: Retrieval-augmented reasoning with lean language models

🔹 Publication Date: Published on Aug 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.11386
• PDF: https://arxiv.org/pdf/2508.11386

🔹 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: StrandDesigner: Towards Practical Strand Generation with Sketch Guidance

🔹 Publication Date: Published on Aug 3

🔹 Abstract: A sketch-based strand generation model using a learnable upsampling strategy and multi-scale adaptive conditioning mechanism outperforms existing methods in realism and precision for hair strand generation. AI-generated summary Realistic hair strand generation is crucial for applications like computer graphics and virtual reality. While diffusion models can generate hairstyles from text or images, these inputs lack precision and user-friendliness. Instead, we propose the first sketch-based strand generation model, which offers finer control while remaining user-friendly. Our framework tackles key challenges, such as modeling complex strand interactions and diverse sketch patterns, through two main innovations: a learnable strand upsampling strategy that encodes 3D strands into multi-scale latent spaces , and a multi-scale adaptive conditioning mechanism using a transformer with diffusion heads to ensure consistency across granularity levels. Experiments on several benchmark datasets show our method outperforms existing approaches in realism and precision. Qualitative results further confirm its effectiveness. Code will be released at [GitHub](https://github.com/fighting-Zhang/StrandDesigner).

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.01650

• PDF: https://arxiv.org/pdf/2508.01650

• Github: https://github.com/fighting-Zhang/StrandDesigner

🔹 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: FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

🔹 Publication Date: Published on Aug 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.11987
• PDF: https://arxiv.org/pdf/2508.11987
• Project Page: https://futurex-ai.github.io/

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/futurex-ai/Futurex-Online
• https://huggingface.co/datasets/futurex-ai/Futurex-Past

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

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

🔹 Title: From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models

🔹 Publication Date: Published on Aug 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.13491
• PDF: https://arxiv.org/pdf/2508.13491

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/NextGenWhu/FinCDM-FinEval-KQA
• https://huggingface.co/datasets/NextGenWhu/FinCDM-CPA-KQA

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

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

🔹 Title: Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

🔹 Publication Date: Published on Aug 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.14811
• PDF: https://arxiv.org/pdf/2508.14811
• Project Page: https://aim-uofa.github.io/Tinker/
• Github: https://github.com/aim-uofa/Tinker

🔹 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: RynnEC: Bringing MLLMs into Embodied World

🔹 Publication Date: Published on Aug 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.14160
• PDF: https://arxiv.org/pdf/2508.14160
• Github: https://github.com/alibaba-damo-academy/RynnEC

🔹 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: Multimodal Referring Segmentation: A Survey

🔹 Publication Date: Published on Aug 1

🔹 Abstract: A survey of multimodal referring segmentation techniques, covering advancements in convolutional neural networks, transformers, and large language models for segmenting objects in images, videos, and 3D scenes based on text or audio instructions. AI-generated summary Multimodal referring segmentation aims to segment target objects in visual scenes, such as images, videos, and 3D scenes, based on referring expressions in text or audio format. This task plays a crucial role in practical applications requiring accurate object perception based on user instructions. Over the past decade, it has gained significant attention in the multimodal community, driven by advances in convolutional neural networks , transformers , and large language models , all of which have substantially improved multimodal perception capabilities. This paper provides a comprehensive survey of multimodal referring segmentation . We begin by introducing this field's background, including problem definitions and commonly used datasets. Next, we summarize a unified meta architecture for referring segmentation and review representative methods across three primary visual scenes, including images, videos, and 3D scenes. We further discuss Generalized Referring Expression (GREx) methods to address the challenges of real-world complexity, along with related tasks and practical applications. Extensive performance comparisons on standard benchmarks are also provided. We continually track related works at https://github.com/henghuiding/Awesome-Multimodal-Referring-Segmentation.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.00265

• PDF: https://arxiv.org/pdf/2508.00265

🔹 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: Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

🔹 Publication Date: Published on Aug 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.14896
• PDF: https://arxiv.org/pdf/2508.14896

🔹 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: NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

🔹 Publication Date: Published on Aug 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.14444
• PDF: https://arxiv.org/pdf/2508.14444

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/nvidia/Nemotron-Post-Training-Dataset-v2

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

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

🔹 Title: DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

🔹 Publication Date: Published on Aug 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.14460
• PDF: https://arxiv.org/pdf/2508.14460

🔹 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: Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

🔹 Publication Date: Published on Aug 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.14187
• PDF: https://arxiv.org/pdf/2508.14187
• Project Page: https://ashiq24.github.io/local-scale-equivariance/
• Github: https://ashiq24.github.io/local-scale-equivariance/

🔹 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: mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10137
• PDF: https://arxiv.org/pdf/2508.10137

🔹 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: CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

🔹 Publication Date: Published on Aug 5

🔹 Abstract: CoTox, a framework integrating LLMs with chain-of-thought reasoning, enhances multi-toxicity prediction by incorporating chemical structure data, biological pathways, and gene ontology terms, improving interpretability and predictive performance in drug development. AI-generated summary Drug toxicity remains a major challenge in pharmaceutical development. Recent machine learning models have improved in silico toxicity prediction, but their reliance on annotated data and lack of interpretability limit their applicability. This limits their ability to capture organ-specific toxicities driven by complex biological mechanisms. Large language models ( LLM s) offer a promising alternative through step-by-step reasoning and integration of textual data, yet prior approaches lack biological context and transparent rationale. To address this issue, we propose CoTox, a novel framework that integrates LLM with chain-of-thought (CoT) reasoning for multi-toxicity prediction . CoTox combines chemical structure data , biological pathways , and gene ontology (GO) terms to generate interpretable toxicity predictions through step-by-step reasoning. Using GPT-4o , we show that CoTox outperforms both traditional machine learning and deep learning model. We further examine its performance across various LLM s to identify where CoTox is most effective. Additionally, we find that representing chemical structures with IUPAC names , which are easier for LLM s to understand than SMILES , enhances the model's reasoning ability and improves predictive performance. To demonstrate its practical utility in drug development, we simulate the treatment of relevant cell types with drug and incorporated the resulting biological context into the CoTox framework. This approach allow CoTox to generate toxicity predictions aligned with physiological responses , as shown in case study. This result highlights the potential of LLM -based frameworks to improve interpretability and support early-stage drug safety assessment. The code and prompt used in this work are available at https://github.com/dmis-lab/CoTox.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.03159

• PDF: https://arxiv.org/pdf/2508.03159

🔹 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