Singular Learning Theory Comprehensive – 2
ForewordWe will continue where we left off. In the last post, I introduced a few important observables along with the setup. We are interested in their…
Latest
What do you love about Sol, or why did you switch to it?
What do you love about Sol, or why did you switch to it?Tibo: Or… what if we gave you $100 in Codex credits if you tell…
How to run Prism Bonsai 27B
According to their GitHub, the file needed is the -Q2_0.gguf version, which requires compiling their version of llama.cpp. Easiest way to download is to use huggingface-cli…
LinkedIn is a cesspool of scammers and identity theft
And Microsoft doesn't care. Comments URL: https://news.ycombinator.com/item?id=48916375 Points: 34 # Comments: 13
RT Tibo: Or… what if we gave you $100 in Codex credits if you tell us what you love about GPT-5.6 Sol or why you switched? Tweet it, claim your gift,…
RT TiboOr… what if we gave you $100 in Codex credits if you tell us what you love about GPT-5.6 Sol or why you switched?Tweet it,…
RT Zephyr: So CXMT is trading at $8.4 on Hyperliquid rn Basically implies a $560B market cap They are officially listing at $85B
RT ZephyrSo CXMT is trading at $8.4 on Hyperliquid rnBasically implies a $560B market capThey are officially listing at $85BJukan: CXMT LIVE IN HYPERLIQUID
Ollama is back in NYC today! It's exciting to see more people and businesses realize the benefits of open models! Ownership. Affordable. Private. Than…
Ollama is back in NYC today! It's exciting to see more people and businesses realize the benefits of open models! Ownership. Affordable. Private. Thank you @Nasdaq…
If you had a 384GB (4x Blackwell), what model would you put on it and why?
Hey guys, Company I work for is actually very interested in spending the money to host our own local model for the team. We expect probably…
remarkable detail: WizardLM disappeared like they never existed. Except they're now at Tencent's Hunyuan team and presumably doing post-training for H…
remarkable detail: WizardLM disappeared like they never existed. Except they're now at Tencent's Hunyuan team and presumably doing post-training for Hy3. it really was a good…
Order-Explicit Linearization of High-Dimensional $U$-Statistics
arXiv:2405.07860v5 Announce Type: replace-cross Abstract: We give an order-explicit large deviation bound for the difference between a high-dimensional $U$-statistic and its H'{a}jek projection. In particular, we…
Cluster-Weighted EDMD
arXiv:2607.12243v1 Announce Type: cross Abstract: Extended Dynamic Mode Decomposition (EDMD) approximates Koopman operators from data, but a single global operator is inefficient when different state-space regions…
CROCS: A Two-Stage Clustering Framework for Behaviour-Centric Consumer Segmentation with Smart Meter Data
arXiv:2601.10494v3 Announce Type: replace Abstract: With grid operators confronting rising uncertainty from renewable integration and a broader push toward electrification, Demand-Side Management (DSM) -- particularly Demand…
Causal Graphs, Markov Properties and Do-calculus for Stochastic Differential Equations
arXiv:2607.12140v1 Announce Type: cross Abstract: Stochastic differential equations (SDEs) are widely used to model continuous-time dynamical systems, but graphical causal models for them are not yet…
Spectral Diffusion Processes
arXiv:2209.14125v3 Announce Type: replace Abstract: Diffusion models have proven to be a flexible and effective framework for modelling probability distributions on finite-dimensional spaces. However, many physical…
Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs
arXiv:2607.11997v1 Announce Type: cross Abstract: Multi-task model merging combines separately trained expert models into a single model that handles all tasks without co-training. Standard practice merges…
MixCIT: A Kernel Based Local-Polynomial Debiased Test for Conditional Independence on Mixed-Type Data
arXiv:2607.12830v1 Announce Type: cross Abstract: Conditional independence testing (CIT) is fundamental to modern statistical inference in areas related to causal discovery and variable selection. While marginal…
Removable Defects: The Economics and Limits of Deliberate Deficiency
arXiv:2607.11983v1 Announce Type: cross Abstract: A specialist tolerates blind spots that a generalist does not. Usually this is treated as a cost to be minimized. We…
Significance-First Splitting: Aligning Treatment Heterogeneity Detection with Honest Estimation
arXiv:2607.03999v2 Announce Type: replace-cross Abstract: Estimating heterogeneous treatment effects (CATE) requires simultaneously detecting effect modification and quantifying estimation uncertainty. Existing tree-based methods make an uneasy trade-off:…
Ensemble Controlled-Flow Filtering for Implicit Data Assimilation
arXiv:2607.12975v1 Announce Type: new Abstract: Data assimilation estimates the state of a dynamical system from model forecasts and incoming observations. Many observation mechanisms, however, are many-to-one,…
Quantification of Credal Uncertainty: A Distance-Based Approach
arXiv:2603.27270v2 Announce Type: replace-cross Abstract: Credal sets, i.e., closed convex sets of probability measures, provide a natural framework to represent aleatoric and epistemic uncertainty in machine…
Dynamic Online Processor-Native Inference for State Estimation
arXiv:2607.12095v1 Announce Type: new Abstract: Sensor-rich data-driven applications increasingly use Bayesian approaches to infer latent states of dynamic systems from noisy sensor measurements and physical models.…
Falsifying Causal Graphs With Outlier Events
arXiv:2607.12145v1 Announce Type: new Abstract: True causal relationships are rarely known, and inferring causal graphs from data is hard. A fundamental challenge is how to assess…
ANGLE: Angular Neural Generative Learning via Engression
arXiv:2607.12833v1 Announce Type: new Abstract: Circular data, representing angles or directions, are frequently encountered in computer vision, biology, geology, and meteorology. Traditional regression targets the conditional…
Contrast-Free ICA and Causal Inference via Wasserstein Distances to the Gaussian
arXiv:2607.12832v1 Announce Type: new Abstract: We study the squared $2$-Wasserstein distance to the standard Gaussian as a non-Gaussianity criterion and use it for linear Independent Component…