RT lily zhangsign up for COLM 2026 before it sells out! for non-local researchers, here's the SF map by @swyx.safety tip: i added poop alerts 💩…
Don't make me post it againJukan: Anthropic just committed the worst self-inflicted wound possible right before its IPO.
test-backend-sampler: skip multi_output_sampling_chain on HIP The new multi_output_sampling_chain test uses top_k, whose backend probs path needs CUB (unavailable on HIP), so sampled_probs is null and the…
Article URL: https://www.neowin.net/news/windows-11-admins-unhappy-as-microsoft-found-installing-unexpected-new-onedrive-photos-app/ Comments URL: https://news.ycombinator.com/item?id=49253329 Points: 26 # Comments: 7
1) I want them to be able to gather detailed telemetry, not just responses API calls, and improve their model faster2) I expect Whale Harness to…
Article URL: https://blog.mozilla.org/security/2026/08/10/updated-gpg-key-for-signing-firefox-and-thunderbird-releases/ Comments URL: https://news.ycombinator.com/item?id=49253250 Points: 13 # Comments: 3
Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the…
User simulators are widely used as scalable environments for training and evaluating interactive assistants. Generating the next user turn is inherently one-to-many: the same profile and…
arXiv:2602.10680v2 Announce Type: replace Abstract: Many real-world datasets contain hidden structure that cannot be detected by simple linear correlations between input features. For example, latent factors…
arXiv:2608.09193v1 Announce Type: new Abstract: Unsupervised time-series domain adaptation (DA) addresses the challenge of transferring a classifier from a labeled source domain to an unlabeled target…
arXiv:2511.11927v2 Announce Type: replace Abstract: Principal Component Analysis (PCA) is a standard tool for extracting a low-rank signal from noisy observations. It is known that applying…
arXiv:2608.09074v1 Announce Type: new Abstract: We develop a new approach to Personalized Federated Learning across heterogeneous clients using Nonparametric Empirical Bayes (NPEB). Leveraging the asymptotic normality…
arXiv:2505.06589v3 Announce Type: replace Abstract: Modern machine learning repeatedly manipulates probability measures: empirical datasets, generated samples, latent distributions, class-conditional laws, particle systems, weights of wide networks…
arXiv:2608.08911v1 Announce Type: new Abstract: Recent advances in Passive Acoustic Monitoring (PAM) offer an opportunity to obtain ecological spatial point-process data at unprecedented scale. However, realizing…
arXiv:2608.07618v1 Announce Type: new Abstract: Stochastic gradient descent for a loss function discontinuous across lower dimensional manifolds is analyzed by studying its differential equation limit.
arXiv:2608.08770v1 Announce Type: new Abstract: Diffusion models are increasingly used as controllable samplers, whose generations can be steered at inference time according to a chosen reward…
arXiv:2605.01729v3 Announce Type: replace-cross Abstract: Generative Flow Networks (GFlowNets) sample diverse structured objects in proportion to reward and have been applied to molecular discovery and biological-sequence…
arXiv:2608.08743v1 Announce Type: new Abstract: Reinforcement learning (RL) seeks to optimize sequential decisions to maximize population-level benefits over time. However, when deployed in high-stakes settings such…
arXiv:2603.07313v4 Announce Type: replace-cross Abstract: Robustness under latent distribution shift remains challenging in partially observable reinforcement learning. We formalize a focused setting where an adversary selects…
arXiv:2608.07648v1 Announce Type: new Abstract: Sampling high-dimensional probability distributions is a central task in scientific computing, with applications ranging from Bayesian inference to statistical physics and…
arXiv:2608.07795v1 Announce Type: new Abstract: Prediction intervals for multi-modal regression with tabular variables, text, images, or other input sources are difficult to calibrate when those sources…
arXiv:2608.08003v1 Announce Type: new Abstract: As machine learned models increase in complexity and expressive power, features of simpler models, such as interpretability and control over the…
arXiv:2608.08424v1 Announce Type: new Abstract: Conformal changepoint localization turns any score into a confidence set for the changepoint with finite-sample coverage. Coverage is universal; efficiency is…
arXiv:2608.08204v1 Announce Type: new Abstract: This work proposes deep nonparametric Instrumental variable quantile regression (IVQR), a two-stage estimator that combines conditional diffusion modeling with a kernel-smoothed…