arXiv:2609.11769v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to analyze and rewrite news, yet current framing…
Deep Learning pioneer Bengio argues the training process itself makes AI dangerous
AI pioneer Yoshua Bengio warns in a new essay that AI agents could learn to deceive, game rules, and hide bad behavior as they get better at optimizing…
Continuous-Time Acoustic Modelling with Neural Controlled Differential Equations
arXiv:2609.11725v1 Announce Type: cross Abstract: Text-to-speech (TTS) models commonly address text–speech alignment by expanding phone-level encoder…
ActSafeGuard: Differentiable and Training-Aligned Constraint Enforcement for Flow-Matching Policies
arXiv:2609.11697v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) and World-Action Models (WAMs) have demonstrated strong capabilities in…
A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNs
arXiv:2609.11713v1 Announce Type: cross Abstract: Artificial neural networks rely on vector-matrix multiplications (VMMs), whose implementation in von…
Language-Augmented Semantic Priors for B-Spline Surface Fitting
arXiv:2609.11708v1 Announce Type: cross Abstract: The use of B-splines and Non-Uniform Rational B-Splines surfaces constitutes the mathematical foundation…
Warrant Theory
arXiv:2609.11667v1 Announce Type: cross Abstract: In this paper, we develop warrant theory as a philosophical discipline concerned with the inferential…
Fly Language Model (FLM) Wires the Full Fruit Fly Connectome Into a Frozen 1.2B LLM, and Its Own Controls Show the Wiring Does Not Help
The Fly Language Model (FLM) drives all 166,700 retained neurons and 25.6 million edges of the MaleCNS fruit fly connectome with token embeddings, then…
Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents
arXiv:2609.11677v1 Announce Type: cross Abstract: Self-evolving runtime harnesses can substantially improve the capabilities of large language model (LLM)…
AI News Brief Hourly Summary 2026-09-12 21h : 11 posts
11 posts published in the last hour 18:32ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding 18:32LoaDiff: Conditional Generation of Electricity Consumption Time Series for Energy Analytics 18:32A Comparative Evaluation of Pre-trained Convolutional Neural Networks for Melanoma Detection 18:32Physics-Informed Neural Networks to Infer the…
ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding
arXiv:2609.11642v1 Announce Type: cross Abstract: Neural audio codecs are a fundamental component of modern speech generation systems. While recent codecs…
LoaDiff: Conditional Generation of Electricity Consumption Time Series for Energy Analytics
arXiv:2609.11639v1 Announce Type: cross Abstract: The energy transition is reshaping residential electricity consumption through the increasing adoption…
A Comparative Evaluation of Pre-trained Convolutional Neural Networks for Melanoma Detection
arXiv:2609.11550v1 Announce Type: cross Abstract: Early diagnosis of melanoma is critical for improving patient survival rates. However, accurately…
Physics-Informed Neural Networks to Infer the Perpendicular Energy Conductivity in the Scrape-Off Layer of Stellarator Devices
arXiv:2609.11628v1 Announce Type: cross Abstract: In this work, we develop an inverse Physics-Informed Neural Network (PINN) framework to infer the…
Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations
arXiv:2609.11573v1 Announce Type: cross Abstract: Boundary representation (B-rep) is the standard format used by modern CAD systems for parametric 3D…
Cross-Lingual Clinical Annotation Projection as Constrained Text Generation: A Six-Language Study
arXiv:2609.11450v1 Announce Type: cross Abstract: Background: To determine whether cross-lingual clinical annotation projection can be formulated as a…
Investigating catastrophic forgetting in sound event classification
arXiv:2609.11447v1 Announce Type: cross Abstract: This work investigates a number of approaches to prevent catastrophic forgetting in class incremental…
Prevalence Determines Precision:Silent Contamination in Detector-Defined Datasets
arXiv:2609.11449v1 Announce Type: cross Abstract: Many ML datasets are constructed by running a detector, heuristic, or model over candidate pools;…