Researchers Guangyi Zou and Roman Vershynin have published a note on the subgaussianity of quantized linear maps. They prove a bounded-differences ine...
Researchers evaluated two machine learning models, ArchesWeather and ArchesWeatherGen, for their ability to simulate climate over long periods. The mo...
Researchers have developed a benchmark for evaluating AI models on real-world formal software verification tasks. They scraped 11,039 property-based t...
Researchers have proposed a new approach called BRo-JEPA to help neural networks learn algebraic rules from visual inputs. They used the MNIST and EMN...
A new library OS substrate called Agent libOS has been proposed for large language model (LLM) agents. It separates three planes: operation admission,...
Researchers have developed a new approach to compressing data in autonomous driving systems. The method, called COMPACT-VA, uses a combination of plan...
Researchers have introduced the Standard Interpretable Model (SIM), a general theory of interpretable machine learning based on Lagrangian mechanics. ...
Researchers have developed a method to audit and repair autonomous driving planners that rely on statistical shortcuts rather than causal relationship...
Researchers examined the transparency of DiffusionGemma, a type of large language model. They found that while it initially appears to have poor varia...
Researchers have proposed a method to detect whether an open-weight checkpoint has been stripped of its refusal mechanism before deployment. The metho...
Researchers propose a new approach to improve the alignment of large language models (LLMs) with their intended policies. They introduce Selective Imp...
Researchers have studied the energy usage of Vision-Language Models (VLMs) on edge hardware. They found that the dominant energy cost is not visual pr...