420

arXiv:2512.13102v2 Announce Type: replace
Abstract: Large Language Models (LLMs) excel at static interactions, where they answer user queries by retrieving knowledge encoded in their parameters. However, in many real-world settings, such as educational tutoring or medical assistance, relevant infor…
330

PLYMOUTH COUNTY, WISCONSIN β€” On a warm fall afternoon, dairy farmer Chris Kestell pushes through prairie brambles taller than himself, tracing a path overgrown with thickets and swarming with bees as he hikes toward a hidden waterway. Though the route is unidentifiable to the untrained eye, Kestell,…
342

arXiv:2503.07982v3 Announce Type: replace
Abstract: High-quality instance and panoptic segmentation has traditionally relied on dense instance-level annotations such as masks, boxes, or points, which are costly, inconsistent, and difficult to scale. Unsupervised and weakly-supervised approaches red…
329

arXiv:2512.19331v1 Announce Type: new
Abstract: Whole Slide Images (WSIs) are typically analyzed using multiple instance learning (MIL) methods. However, the scale and heterogeneity of WSIs generate highly redundant and dispersed information, making it difficult to identify and integrate discrimina…
319

Demis Hassabis, CEO of Google DeepMind, summed it up in three words: β€œThis is embarrassing.”   Hassabis was replying on X to an overexcited post by SΓ©bastien Bubeck, a research scientist at the rival firm OpenAI, announcing that two mathematicians had used OpenAI’s latest large language model, GPT-5…
319

arXiv:2508.14075v2 Announce Type: replace
Abstract: In a previous paper, we proposed an introduction to the explainability of Graph Spectral Clustering results for textual documents, given that document similarity is computed as cosine similarity in term vector space.
In this paper, we generalize…
232

Join Stephen Cass, Dina Genkina, and Kohava Mendelsohn as they discuss whether AI spells the end of distinct programming languages as we know it. IEEE Spectrum publishes a respected annual ranking of the year’s Top Programming Languagesβ€”but could this year be our last? This recording of the live web…
227

arXiv:2512.18551v1 Announce Type: new
Abstract: In language modeling, neologisms are new tokens trained to represent a concept not already included in a given model's vocabulary. Neologisms can be used to encourage specific behavior in models, for example by appending prompts with "Give me a neolog…
222

arXiv:2512.18068v1 Announce Type: new
Abstract: Imitation learning (IL) has shown immense promise in enabling autonomous dexterous manipulation, including learning surgical tasks. To fully unlock the potential of IL for surgery, access to clinical datasets is needed, which unfortunately lack the ki…