PULSE: Our community science stream

  • CODENov. 1, 2025, 5:50 a.m.
    LIMIT

    This repository contains the official resources for the paper "On the Theoretical Limitations of Embedding-based Retrieval". This work introduces the LIMIT dataset, designed to stress-test …

  • BOOKMARKOct. 29, 2025, 2:26 a.m.
    Amortized variational transdimensional inference

    The expressiveness of flow-based models combined with stochastic variational inference (SVI) has expanded the application of optimization-based Bayesian inference to highly complex problems. However, despite …

  • ENDORSEMENTOct. 28, 2025, 10:04 p.m.
    AI-Generated Video Detection via Perceptual Straightening

    The rapid advancement of generative AI enables highly realistic synthetic videos, posing significant challenges for content authentication and raising urgent concerns about misuse. Existing detection …

  • BOOKMARKOct. 27, 2025, 10:34 p.m.
    GraphGhost: Tracing Structures Behind Large Language Models

    Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, yet the structural mechanisms underlying these abilities remain under explored. In this work, we introduce GraphGhost, a …

  • CLUBOct. 23, 2025, 8:25 p.m.
    ANL-AI-Reading-Group

    Agentic AI Reading Group @ ANL

    Kayewords: Agent, AI
  • ENDORSEMENTOct. 21, 2025, 5:37 a.m.
    The Markovian Thinker

    Reinforcement learning (RL) has recently become a strong recipe for training reasoning LLMs that produce long chains of thought (LongCoT). Yet the standard RL "thinking …

  • ENDORSEMENTOct. 9, 2025, 8:40 p.m.
    A Survey of Small Language Models

    Small Language Models (SLMs) have become increasingly important due to their efficiency and performance to perform various language tasks with minimal computational resources, making them …

  • ENDORSEMENTOct. 9, 2025, 3:47 a.m.
    Less is More: Recursive Reasoning with Tiny Networks

    Hierarchical Reasoning Model (HRM) is a novel approach using two small neural networks recursing at different frequencies. This biologically inspired method beats Large Language models …

  • CLUBSept. 29, 2025, 9:38 a.m.
    Cambridge Extragalactic

    Extragalactic group at the Kavli Institute for Cosmology, Cambridge

    Kayewords: extragalactic, agn, galaxies, high-redshift, observations
  • ENDORSEMENTSept. 22, 2025, 12:13 a.m.
    Pre-training under infinite compute

    Since compute grows much faster than web text available for language model pre-training, we ask how one should approach pre-training under fixed data and no …

  • ENDORSEMENTSept. 19, 2025, 9:52 p.m.
    Scaling Laws for Uncertainty in Deep Learning

    Deep learning has recently revealed the existence of scaling laws, demonstrating that model performance follows predictable trends based on dataset and model sizes. Inspired by …