Tootfinder

IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
Xu Guo, Tianyi Liang, Tong Jian, Xiaogui Yang, Ling-I Wu, Chenhui Li, Zhihui Lu, Qipeng Guo, Kai Chen
https://arxiv.org/abs/2508.04632

IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
Reinforcement Learning with Verifiable Rewards (RLVR) improves instruction following capabilities of large language models (LLMs), but suffers from training inefficiency due to inadequate difficulty assessment. Moreover, RLVR is prone to over-optimization, where LLMs exploit verification shortcuts without aligning to the actual intent of user instructions. We introduce Instruction Following Decorator (IFDecorator}, a framework that wraps RLVR training into a robust and sample-efficient pipeline…

Notes and computations on forbidden differences
Christian Dean, Haley Havard, Elizabeth Hawkins, Patch Heard, Andrew Lott, Alex Rice
https://arxiv.org/abs/2508.03650 https://

Notes and computations on forbidden differences
We explore from several perspectives the following question: given $X\subseteq \mathbb{Z}$ and $N\in \mathbb{N}$, what is the maximum size $D(X,N)$ of $A\subseteq \{1,2,\dots,N\}$ before $A$ is forced to contain two distinct elements that differ by an element of $X$? The set of forbidden differences, $X$, is called \textit{intersective} if $D(X,N)=o(N)$, with the most well-studied examples being $X=S=\{n^2: n\in \mathbb{N}\}$ and $X=\mathcal{P}-1=\{p-1: p\text{ prime}\}$. In addition to some ne…

Anyone from Microsoft following me?
I’m going to leave GitHub (I’ve been a user since the beta days) and will incessantly ask everyone I know to leave it as well if you don’t roll back the “can’t opt out” force-feeding of “AI” nonsense.
You should also have no integration or collaboration with Xai at all, ever.
Make your management have some sense, this is hostile and disgusting and wrong.
#github

Spatial-Temporal-Spectral Mamba with Sparse Deformable Token Sequence for Enhanced MODIS Time Series Classification
Zack Dewis, Zhengsen Xu, Yimin Zhu, Motasem Alkayid, Mabel Heffring, Lincoln Linlin Xu
https://arxiv.org/abs/2508.02839

Spatial-Temporal-Spectral Mamba with Sparse Deformable Token Sequence for Enhanced MODIS Time Series Classification
Although MODIS time series data are critical for supporting dynamic, large-scale land cover land use classification, it is a challenging task to capture the subtle class signature information due to key MODIS difficulties, e.g., high temporal dimensionality, mixed pixels, and spatial-temporal-spectral coupling effect. This paper presents a novel spatial-temporal-spectral Mamba (STSMamba) with deformable token sequence for enhanced MODIS time series classification, with the following key contrib…

A revamped Inside the NFL, produced by NFL Films, will debut September 8 on Elon Musk's X, with at least 10 short episodes airing weekly on the platform (Alex Weprin/The Hollywood Reporter)
https://www.hollywoodreporter.com/business

‘Inside the NFL’ Gets Reboot as an X Original Series
Ryan Clark will host the show, which will be reimagined for the Elon Musk-owned platform as a short-form series with new episodes throughout each week of the NFL season.

R2GenKG: Hierarchical Multi-modal Knowledge Graph for LLM-based Radiology Report Generation
Futian Wang, Yuhan Qiao, Xiao Wang, Fuling Wang, Yuxiang Zhang, Dengdi Sun
https://arxiv.org/abs/2508.03426

R2GenKG: Hierarchical Multi-modal Knowledge Graph for LLM-based Radiology Report Generation
X-ray medical report generation is one of the important applications of artificial intelligence in healthcare. With the support of large foundation models, the quality of medical report generation has significantly improved. However, challenges such as hallucination and weak disease diagnostic capability still persist. In this paper, we first construct a large-scale multi-modal medical knowledge graph (termed M3KG) based on the ground truth medical report using the GPT-4o. It contains 2477 enti…

This is only true for some flavors of "big accounts."
A number of the people I follow with thousands of followers are ONLY on the #Fediverse and most of the rest are only here and on Bluesky. I routinely block people here and on Bluesky (and across the bridge) who pull in the sewage from X and dump it in either place.
I'm not really interested in following people that wa…

Stimulated Brillouin Amplification with Flying Focus
Zhaohui Wu, Xiaoming Zeng, Zhaoli Li, Xiaodong Wang, Xiao Wang, Jie Mu, Yanlei Zuo, Kainan Zhou, Hao Peng, C. Riconda, S. Weber
https://arxiv.org/abs/2508.04121

Stimulated Brillouin Amplification with Flying Focus
Material damage thresholds pose a fundamental limit to chirped pulse amplification (CPA) in high-power laser systems. Plasma-based amplification via stimulated Brillouin scattering (SBS) offers a damage-free alternative, yet its effectiveness has been hindered by instabilities that constrain interaction length. In this study, we report the first experimental demonstration of SBS amplification driven by a flying focus in a 3-mm plasma channel. The flying focus is generated using chromatic aberra…

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
Chenyang Wang, Liang Wen, Shousheng Jia, Xiangzheng Zhang, Liang Xu
https://arxiv.org/abs/2508.03178

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
While advancements in the reasoning abilities of LLMs have significantly enhanced their performance in solving mathematical problems, coding tasks, and general puzzles, their effectiveness in accurately adhering to instructions remains inconsistent, particularly with more complex directives. Our investigation identifies lazy reasoning during the thinking stage as the primary factor contributing to poor instruction adherence. To mitigate this issue, we propose a comprehensive framework designed …

Nepal says it is blocking most major social media platforms, including Facebook, X, and YouTube, after the companies failed to register with the government (Binaj Gurubacharya/Associated Press)
https://apnews.com/article/nepal-ban-social-media-plat…

Nepal blocks Facebook, X, YouTube and others for failing to register with the government
Nepal's government says it is blocking most social media platforms, including Facebook, X and YouTube, because they failed to register with the government. Nepal's Minister for Communication and Information said about two dozen platforms were repeatedly notified to register. TikTok, Viber, and three other platforms are allowed to operate because they have registered. The government has introduced a bill in parliament to ensure social platforms are managed responsibly. Rights groups criticize th…