Gratitude and ambition aren’t opposites. They’re the only two things that keep each other from becoming dangerous. Ed Catmull spent twenty years trying to make a computer-animated film. He’d wanted it since he was a kid watching Disney movies in the 1950s, realized he couldn’t draw, and decided to find another way. He got a PhD in computer science. He worked at Lucasfilm. He co-founded Pixar with Steve Jobs in 1986 and spent the next nine years building […]

Ver mais

arXiv:2602.05059v1 Announce Type: new Abstract: Large Language Models are increasingly used by students to explore advanced material in computer science, including graph theory. As these tools become integrated into undergraduate and graduate coursework, it is important to understand how reliably they support mathematically rigorous thinking. This study examines the performance of a LLM on two related graph theoretic problems: a solved problem concerning the gracefulness of line graphs and an open problem for which no solution is currently […]

Ver mais

arXiv:2601.17097v1 Announce Type: new Abstract: Real-time automatic speech recognition systems are increasingly integrated into interactive applications, from voice assistants to live transcription services. However, scaling these systems to support multiple concurrent clients while maintaining low latency and high accuracy remains a major challenge. In this work, we present SWIM, a novel real-time ASR system built on top of OpenAI’s Whisper model that enables true model-level parallelization for scalable, multilingual transcription. SWIM supports multiple concurrent audio streams without modifying […]

Ver mais

Go 1.21 includes a preview of a change to for loop scoping that we plan to ship in Go 1.22, removing one of the most common Go mistakes. The Problem If you’ve written any amount of Go code, you’ve probably made the mistake of keeping a reference to a loop variable past the end of its iteration, at which point it takes on a new value that you didn’t want. For example, consider this program: func main() { […]

Ver mais

Reinforcement Learning (RL) agents often struggle in real-world applications where environmental conditions are non-stationary, particularly when reward functions shift or the available action space expands. This paper introduces MORPHIN, a self-adaptive Q-learning framework that enables on-the-fly adaptation without full retraining. By integrating concept drift detection with dynamic adjustments to learning and exploration hyperparameters, MORPHIN adapts agents to changes in both the reward function and on-the-fly expansions of the agent’s action space, while preserving prior policy knowledge to prevent […]

Ver mais

arXiv:2603.05582v1 Announce Type: new Abstract: The issue of algorithmic biases in deep learning has led to the development of various debiasing techniques, many of which perform complex training procedures or dataset manipulation. However, an intriguing question arises: is it possible to extract fair and bias-agnostic subnetworks from standard vanilla-trained models without relying on additional data, such as unbiased training set? In this work, we introduce Bias-Invariant Subnetwork Extraction (BISE), a learning strategy that identifies and isolates “bias-free” subnetworks […]

Ver mais

arXiv:2603.02263v1 Announce Type: new Abstract: World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the same environment without any parameter sharing or coordination. After training, their internal representations exhibit a striking emergent property: the two latent spaces are related by an approximate linear isometry, enabling transparent translation between them. This geometric consensus survives large viewpoint shifts and scant overlap in raw pixels. […]

Ver mais