PULSE: Our community science stream

  • ENDORSEMENTJuly 24, 2026, 10:33 p.m.
    An Exam for Active Observers

    Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have …

  • ENDORSEMENTJuly 9, 2026, 10:40 p.m.
    AdaJEPA: An Adaptive Latent World Model

    Latent world models enable planning from high-dimensional observations by predicting future states in a compact latent space. However, these models are typically kept frozen at …

  • ENDORSEMENTJune 25, 2026, 5:31 a.m.
    Causal World Modeling for Robot Control

    This work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively, video world models provide the …

  • CODEJune 13, 2026, 2:11 a.m.
    PixelRAG

    PixelRAG renders documents — web pages, PDFs, images — as screenshots and retrieves over the images directly. Visual structure that HTML parsing throws away — …

  • ENDORSEMENTJune 8, 2026, 8:38 p.m.
    Scaling Law of Neural Koopman Operators

    Data-driven neural Koopman operator theory has emerged as a powerful tool for linearizing and controlling nonlinear robotic systems. However, the performance of these data-driven models …

  • ENDORSEMENTJune 2, 2026, 6:27 a.m.
    CalArena: A Large-Scale Post-Hoc Calibration Benchmark

    Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated. Post-hoc calibration provides a simple and widely used …

  • ENDORSEMENTMay 30, 2026, 7:12 a.m.
    MeMo: Memory as a Model

    Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications require …

  • BOOKMARKMay 26, 2026, 10:20 p.m.
    Language Models Need Sleep

    Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study a …

  • ENDORSEMENTMay 24, 2026, 9:23 a.m.
    Follow the Mean: Reference-Guided Flow Matching

    Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching admits a different control interface: adaptation …

  • ENDORSEMENTMay 22, 2026, 11:26 p.m.
    Conditioning Gaussian Processes on Almost Anything

    Gaussian processes (GPs) offer a principled probabilistic model over functions, but exact inference is restricted to the linear-Gaussian regime. We establish an explicit equivalence between …

  • ENDORSEMENTMay 22, 2026, 1:12 a.m.
    Metropolis-Adjusted Diffusion Models

    Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy for reducing this …

  • BOOKMARKMay 17, 2026, 6:26 p.m.
    Corner Charge Fluctuations in Higher Dimensions

    Measuring charge fluctuations within a subregion provides a powerful probe of quantum many-body systems. In two spatial dimensions, the shape dependence of the dimensionless corner …

  • BOOKMARKMay 13, 2026, 10:06 p.m.
    LILO: Bayesian Optimization with Natural Language Feedback

    Many real-world optimization problems are guided by complex, subjective preferences that are difficult to express as explicit closed-form objectives. In response, we introduce Language-in-the-Loop Optimization …

  • ENDORSEMENTMay 12, 2026, 9:07 p.m.
    BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models

    Low-Rank Adaptation (LoRA) has become the standard for fine-tuning large pre-trained models at reduced computational cost. However, its low-rank point-estimate updates limit expressiveness, leave a …