Tootfinder

Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation
Chaojun Nie, Jun Zhou, Guanxiang Wang, Shisong Wud, Zichen Wang
https://arxiv.org/abs/2509.20162

Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation
Large language models (LLMs) often exhibit limited performance on domain-specific tasks due to the natural disproportionate representation of specialized information in their training data and the static nature of these datasets. Knowledge scarcity and temporal lag create knowledge gaps for domain applications. While post-training on domain datasets can embed knowledge into models, existing approaches have some limitations. Continual Pre-Training (CPT) treats all tokens in domain documents with…

We bought into the "post scarcity" narrative because digital tech feels so magic and ethereal but we need to get back to an understanding of the material costs and effects of those systems. They are not very post-scarce in reality.

RE: https://tldr.nettime.org/@tante/115555052555644231
In fact: The "post scarcity" that the western, rich countries feel mostly comes at the cost of the global majority. Colonialism always felt "post-scarcy". Because it forces the cost …

QPADL: Post-Quantum Private Spectrum Access with Verified Location and DoS Resilience
Saleh Darzi, Saif Eddine Nouma, Kiarash Sedghighadikolaei, Attila Altay
https://arxiv.org/abs/2510.03631

QPADL: Post-Quantum Private Spectrum Access with Verified Location and DoS Resilience
With advances in wireless communication and growing spectrum scarcity, Spectrum Access Systems (SASs) offer an opportunistic solution but face significant security challenges. Regulations require disclosure of location coordinates and transmission details, exposing user privacy and anonymity during spectrum queries, while the database operations themselves permit Denial-of-Service (DoS) attacks. As location-based services, SAS is also vulnerable to compromised or malicious users conducting spoo…

World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
Junjin Xiao, Yandan Yang, Xinyuan Chang, Ronghan Chen, Feng Xiong, Mu Xu, Wei-Shi Zheng, Qing Zhang
https://arxiv.org/abs/2509.24948

World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
Vision-Language-Action (VLA) models trained via imitation learning suffer from significant performance degradation in data-scarce scenarios due to their reliance on large-scale demonstration datasets. Although reinforcement learning (RL)-based post-training has proven effective in addressing data scarcity, its application to VLA models is hindered by the non-resettable nature of real-world environments. This limitation is particularly critical in high-risk domains such as industrial automation,…