The daily ledger

Credit Risk: What Are We Actually Measuring?

Let’s start with a loan and work out what PD, LGD, and EAD tell us about losses and bank capital. The post Credit Risk: What Are We Actually Measuring? appeared first on Towards Data Science.

Reflection's Beam Is the New Open-Weight Model Everyone Is Talking About

A 501B model that only activates 23B parameters per token sounds like a bargain, until you look at what it takes to host. The post Reflection's Beam Is the New Open-Weight Model Everyone Is Talking About appeared first…

Our AI Has an Invisible Footprint — Let's see How to Measure It

The hardest part is no longer getting the numbers. It's deciding what to do with them. The post Our AI Has an Invisible Footprint — Let's see How to Measure It appeared first on Towards Data Science.

Let Decision Models Watch Your Agents

A hands-on guide to detecting behavioral anomalies from an agent’s evolving execution history The post Let Decision Models Watch Your Agents appeared first on Towards Data Science.

😺 Microsoft's binding AI school deal

M$^\star$: Every Task Deserves Its Own Memory Harness

arXiv:2604.11811v3 Announce Type: replace-cross Abstract: Large language model agents rely on a memory harness to write, organize, retrieve, and use past experience. A harness that works for one task often fails on…

Generative SDEs with Trainable Diffusion and Density-Based Losses

arXiv:2610.41243v1 Announce Type: new Abstract: We develop a divergence-kernel method for jointly optimizing neural SDE drift and diffusion fields and the initial Gaussian distribution, using losses that depend directly…

Conditional Neural SDEs for Financial Time-Series Generation

arXiv:2610.41405v1 Announce Type: cross Abstract: Conditional generation of time-series paths is a central problem in probabilistic modeling, where the goal is to simulate future trajectories that are both realistic and…

Recursive Code Evolution for Task-Oriented Semantic Communications

arXiv:2610.29641v2 Announce Type: replace-cross Abstract: Semantic communication jointly optimizes inference accuracy, channel use, and computation, yet the underlying communication program is typically specified before…

h1: A Taste of the Bitter Lesson in Automated Theorem Proving

arXiv:2610.35962v2 Announce Type: replace Abstract: While progress in informal mathematics has come largely from scaling the chain-of-thought and agentic reasoning of frontier language models, formal theorem proving has…

DEX: Digit-Level Early Exit for Energy-Efficient MSDF Neural Network Inference

arXiv:2610.11748v2 Announce Type: replace-cross Abstract: U-Net inference for brain-tumor segmentation requires billions of multiply-accumulate operations, motivating hardware that can reduce computation dynamically…

A Nearly Quadratic Lower Bound for Linear Optimization over Convex Bodies in the Membership Oracle Model

arXiv:2609.30215v2 Announce Type: replace-cross Abstract: We prove nearly quadratic lower bounds for randomized algorithms for linear optimization and uniform sampling over convex bodies in the membership oracle model.…

Steering Vectors as a Training Signal in LLM Post-Training

arXiv:2610.40998v1 Announce Type: new Abstract: Steering vectors (SVs) are residual-stream directions that shift the behavior of LLMs when added to hidden states at inference time. While prior work has mainly used SVs…

Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis

arXiv:2605.00826v2 Announce Type: replace-cross Abstract: Text-to-video retrieval enables users to find relevant video content using natural language queries, a task that has grown increasingly important with the rapid…

Physiological Trajectories and Observation Patterns in ICU Mortality Prediction: Transportability Under Changing Measurement Conditions

arXiv:2610.42126v1 Announce Type: new Abstract: Objective: To distinguish the transferable predictive value of physiological trajectories from that of observation patterns in ICU mortality prediction, and to assess…

On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization

arXiv:2607.02834v2 Announce Type: replace Abstract: Molecular optimization often starts from a pretrained generative model that captures a broad prior over valid molecular structures. At test time, however, the goal is…

Accurate and Auditable ECG Classification via Visibility Graph Neural Networks

arXiv:2610.41795v1 Announce Type: new Abstract: Physicians read electrocardiograms (ECGs) from waveform shape and timing, yet accurate deep-learning classifiers rarely show which waveform regions drive their…

Monte Carlo Random Walk Kernel

arXiv:2610.40956v1 Announce Type: new Abstract: We introduce the Monte Carlo Random Walk Kernel (MCRWK), an estimator whose per-pair cost is independent of graph size and derived directly from the random walk kernel…

TaxoMFM: A Taxonomy-Aware Foundation Model for the Human Gut Microbiome

arXiv:2610.39316v2 Announce Type: replace Abstract: Existing gut microbiome foundation models typically use flat taxon representations, limiting their ability to exploit known taxonomic hierarchies. We introduce…

Normative Deviation Modeling for EEG-based Depression Detection

arXiv:2610.37338v2 Announce Type: replace Abstract: Web-enabled digital health services are expanding access to physiological monitoring and mental health screening. However, electroencephalography (EEG)-based major…