arXiv:2604.08639v1 Announce Type: new Abstract: Uncertainty quantification (UQ) is essential for deploying deep learning models in safety critical applications, yet no consensus exists on which UQ method performs best across different data modalities and distribution shifts. This paper presents a comprehensive benchmark of ten widely used UQ baselines including MC Dropout, SWAG, ensemble methods, temperature scaling, energy based OOD, Mahalanobis, hyperbolic classifiers, ENN, Taylor Sensus, and split conformal prediction against a simplified yet highly effective variant of VOLTA […]

Ver mais

We gotta talk about AI as a programming tool for the arts Chris Ashworth is the creator and CEO of QLab, a macOS software package for “cue-based, multimedia playback” which is designed to automate lighting and audio for live theater productions. I recently started following him on TikTok where he posts about his business and theater automation in general – Chris founded the Voxel theater in Baltimore which QLab use as a combined performance venue, teaching hub and […]

Ver mais

How are you, hacker? 🪐Want to know what’s trending right now?: The Techbeat by HackerNoon has got you covered with fresh content from our trending stories of the day! Set email preference here. ## Microsoft’s AutoDev: The AI That Builds, Tests, and Fixes Code on Its Own By @microsoft [ 27 Min read ] Microsoft’s AutoDev uses AI agents to write, test, and fix code autonomously, hitting 91.5% on HumanEval in Docker. Read More. How CMOs Win CFO […]

Ver mais

arXiv:2604.01329v1 Announce Type: new Abstract: Model merging provides a way of cheaply combining individual models to produce a model that inherits each individual’s capabilities. While some merging methods can approach the performance of multitask training, they are often heuristically motivated and lack theoretical justification. A principled alternative is to pose model merging as a layer-wise optimization problem that directly minimizes interference between tasks. However, this formulation requires estimating per-layer covariance matrices from data, which may not be available […]

Ver mais

arXiv:2603.15666v1 Announce Type: new Abstract: Existing memory systems for language agents address memory management: how to retrieve and page more information within a context budget. We address a complementary problem — memory utility: what experience is worth keeping, and how it should change agent behavior. We present Atlas, a memory kernel that compiles accumulated task experience into an agent’s instruction structure — without fine-tuning, RAG, or human intervention. Memory is distillation, not storage; delivery is instruction rewriting, not […]

Ver mais

Across the financial technology sector, large institutions are facing a hard reality. Systems that were built decades ago for stability and control are now under pressure to deliver flexibility, cost efficiency, and faster change. Banks and market infrastructure firms continue to depend on legacy data centers to process sensitive trade data, where outages and errors are not an option. Yet rising operational costs and growing demand for agility have made cloud adoption less of a future goal and […]

Ver mais

Slump in the market divides good projects and bad projects. Whereas the vast majority of cryptocurrencies are struggling, there are some memecoins that exhibit odd persistence and accretion trends that are historically followed by significant movements. There are three tokens now which have different bullish indicators. PEPE at $0.000006619 holds on to $2.78B experiencing a strong increase in holders. BONK is trading with accumulation at the price of $0.00001177 with the market capital of $1.04B, despite the other […]

Ver mais

arXiv:2601.07792v1 Announce Type: cross Abstract: Portfolio optimization under cardinality constraints transforms the classical Markowitz mean-variance problem from a convex quadratic problem into an NP-hard combinatorial optimization problem. This paper introduces a novel approach using THRML (Thermodynamic HypergRaphical Model Library), a JAX-based library for building and sampling probabilistic graphical models that reformulates index tracking as probabilistic inference on an Ising Hamiltonian. Unlike traditional methods that seek a single optimal solution, THRML samples from the Boltzmann distribution of high-quality portfolios […]

Ver mais

arXiv:2504.09629v3 Announce Type: replace-cross Abstract: Layer-wise PTQ is a promising technique for compressing large language models (LLMs), due to its simplicity and effectiveness without requiring retraining. However, recent progress in this area is saturating, underscoring the need to revisit its core limitations and explore further improvements. We address this challenge by identifying a key limitation of existing layer-wise PTQ methods: the growth of quantization errors across layers significantly degrades performance, particularly in low-bit regimes. To address this fundamental […]

Ver mais

We study the complexity of smoothed agnostic learning, recently introduced by~cite{CKKMS24}, in which the learner competes with the best classifier in a target class under slight Gaussian perturbations of the inputs. Specifically, we focus on the prototypical task of agnostically learning halfspaces under subgaussian distributions in the smoothed model. The best known upper bound for this problem relies on $L_1$-polynomial regression and has complexity $d^{tilde{O}(1/σ^2) log(1/ε)}$, where $σ$ is the smoothing parameter and $ε$ is the excess error. […]

Ver mais