🔹 Title: When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

🔹 Publication Date: Published on Aug 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.03365
• PDF: https://arxiv.org/pdf/2508.03365

🔹 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: Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences

🔹 Publication Date: Published on Aug 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.03542
• PDF: https://arxiv.org/pdf/2508.03542

🔹 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: Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

🔹 Publication Date: Published on Aug 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.07785
• PDF: https://arxiv.org/pdf/2508.07785
• Github: https://github.com/inclusionAI/GroveMoE/

🔹 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 Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

🔹 Publication Date: Published on Aug 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.07407
• PDF: https://arxiv.org/pdf/2508.07407

🔹 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: MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs

🔹 Publication Date: Published on Aug 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.05257
• PDF: https://arxiv.org/pdf/2508.05257

🔹 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: Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

🔹 Publication Date: Published on Aug 5

🔹 Abstract: Goedel-Prover-V2, a series of open-source language models, achieves state-of-the-art performance in automated theorem proving through scaffolded data synthesis, verifier-guided self-correction, and model averaging. AI-generated summary We introduce Goedel-Prover-V2, a series of open-source language models that set a new state-of-the-art in automated theorem proving . Built on the standard expert iteration and reinforcement learning pipeline, our approach incorporates three key innovations: (1) Scaffolded data synthesis : We generate synthetic tasks of increasing difficulty to train the model to master increasingly complex theorems; (2) Verifier-guided self-correction : We enable the model to iteratively revise its proofs by leveraging feedback from the Lean compiler; (3) Model averaging : We merge model checkpoints to mitigate the decrease in model output diversity in later stages of training. Our small model, Goedel-Prover-V2-8B, reaches 84.6% pass@32 on MiniF2F and outperforms DeepSeek-Prover-V2-671B under the same metric, despite being 80X smaller. Our flagship model, Goedel-Prover-V2-32B, achieves 88.1% on MiniF2F at pass@32 in standard mode and 90.4% in self-correction mode, outperforming prior SOTA by a large margin. Additionally, our flagship model solves 86 problems on PutnamBench at pass@184 , securing the first place among open-source models on the leaderboard, surpassing DeepSeek-Prover-V2-671B's record of solving 47 problems by pass@1024 with a significantly smaller model size and compute budget. At the time of its release (July-August 2025), Goedel-Prover-V2 achieves the strongest overall performance among all open-source theorem provers. It also ranks among the top-performing models--including closed-source systems with publicly reported performance--under a constrained test-time compute budget. Our models, code, and data are released at https://github.com/Goedel-LM/Goedel-Prover-V2.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.03613

• PDF: https://arxiv.org/pdf/2508.03613

🔹 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: Compressing Chain-of-Thought in LLMs via Step Entropy

🔹 Publication Date: Published on Aug 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.03346
• PDF: https://arxiv.org/pdf/2508.03346

🔹 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: Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

🔹 Publication Date: Published on Aug 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.06059
• PDF: https://arxiv.org/pdf/2508.06059

🔹 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: TextQuests: How Good are LLMs at Text-Based Video Games?

🔹 Publication Date: Published on Jul 31

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2507.23701
• PDF: https://arxiv.org/pdf/2507.23701
• Project Page: https://textquests.ai
• Github: https://github.com/centerforaisafety/textquests

🔹 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: Spectrum Projection Score: Aligning Retrieved Summaries with Reader Models in Retrieval-Augmented Generation

🔹 Publication Date: Published on Aug 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.05909
• PDF: https://arxiv.org/pdf/2508.05909

🔹 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: Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face

🔹 Publication Date: Published on Aug 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.06811
• PDF: https://arxiv.org/pdf/2508.06811

🔹 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: Matrix-3D: Omnidirectional Explorable 3D World Generation

🔹 Publication Date: Published on Aug 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.08086
• PDF: https://arxiv.org/pdf/2508.08086

🔹 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: Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

🔹 Publication Date: Published on Aug 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.05615
• PDF: https://arxiv.org/pdf/2508.05615
• Project Page: https://zju-real.github.io/gui-rcpo/
• Github: https://github.com/zju-real/gui-rcpo

🔹 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: UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

🔹 Publication Date: Published on Aug 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.05399
• PDF: https://arxiv.org/pdf/2508.05399

🔹 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: Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

🔹 Publication Date: Published on Aug 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09138
• PDF: https://arxiv.org/pdf/2508.09138
• Project Page: https://aim-uofa.github.io/dLLM-MidTruth/
• Github: https://github.com/aim-uofa/dLLM-MidTruth

🔹 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: Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

🔹 Publication Date: Published on Aug 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.07976v1
• PDF: https://arxiv.org/pdf/2508.07976
• Github: https://github.com/inclusionAI/ASearcher

🔹 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: HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches

🔹 Publication Date: Published on Aug 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.08088
• PDF: https://arxiv.org/pdf/2508.08088
• Github: https://github.com/plageon/HierSearch

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/zstanjj/HierSearch-Datasets

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

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

🔹 Title: AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators

🔹 Publication Date: Published on Aug 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09101
• PDF: https://arxiv.org/pdf/2508.09101

🔹 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: WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

🔹 Publication Date: Published on Aug 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.05748
• PDF: https://arxiv.org/pdf/2508.05748
• Github: https://github.com/Alibaba-NLP/WebAgent

🔹 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: Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

🔹 Publication Date: Published on Aug 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.08791
• PDF: https://arxiv.org/pdf/2508.08791
• Github: https://github.com/bytedance/FTRL

🔹 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: CharacterShot: Controllable and Consistent 4D Character Animation

🔹 Publication Date: Published on Aug 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.07409
• PDF: https://arxiv.org/pdf/2508.07409
• Github: https://github.com/Jeoyal/CharacterShot

🔹 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