The Archive

Transformer-based neural operator (RheOPT) pretrained on Newtonian flows for data-efficient few-shot prediction of non-Newtonian fluid dynamics.

Study of metadata composition effects on LLM-generated museum descriptions reveals field-level grounding challenges.

RULES: neuro-symbolic model for interpretable sequential event prediction via learned temporal rules.

A* search with domain-specific heuristics outperforms SAT/IP solvers on Flood-It puzzle optimization, offering generalizable algorithmic insights.

The Eiliko robot toy. | Photo by Sean Hollister / The Verge Eiliko, a cute robot charm you can hang on your bag with built-in AI conversations, turned out to be a security nightmare. It told owners that "your secrets are safe with me," but hackers could easily read complete transcripts of everything we told the toy, and that was just the beginning. The Verge and security researcher Sammy Azdoufal spent over a month trying to get in contact with the company, including emails to Energize Lab CEO and founder Shaw Yeung. Nobody would answer our questions. Now, the company is finally breaking its ...

SCOPE compiles natural-language policies into neurosymbolic programs for stable, efficient LLM agent governance over multi-turn trajectories.

Multi-directional Perturbation-Rewrite Search framework uses LLMs to automate heuristic design for NP-hard combinatorial optimization with factorized transformations.

Neural network transistor models for 3nm nanosheet accelerate SPICE simulation but require validation in full EDA tool flows for standard cell characterization.

Teacher-student analysis isolates effects of locality and weight sharing in CNNs, showing interaction with image correlation structure.

Sparse autoencoders convert opaque neural AI-text detectors into interpretable classifiers operating on human-readable concepts for high-stakes deployment.

This paper describes our submission to the WMT 2026 Multilingual Instruction Shared Task. We adapt Qwen3-8B with LoRA using organiser-provided data, EuroAlpaca, a multilingual instruction dataset created through task-preserving localisation, and CrossEuroAlpaca, a cross-lingual augmentation that assigns different source and target languages to instructions, contexts and responses. Our system targets open-ended question answering (QA-OEG) in ten shared-task languages represented in the auxiliary data. Under matched decoding, adaptation improves the mean Gemma-4 judge score on target-language Q...

PUN neural operator learns noise-aware value fields for robot planning under stochastic control constraints via screened-Poisson formulation.

Neural implicit energy optimization regularizes signed distance fields for large-scale LiDAR scene reconstruction.

PaPi integration scheme enables parallel time-stepping for physics-informed neural networks solving PDEs.

OptScientist framework discovers symbolic optimization laws from data using neural inference and LLM-agentic exploration.

Theoretical convergence analysis of SGD in deep linear neural networks with regularized squared loss.

Closed-loop forecasting with spiking neural networks and state-space models for time-series prediction with temporal dependencies.

Physics-informed neural framework discovers extreme scenarios via data-driven dynamics inference with geometry-agnostic learned representations.

LocaLeJEPA extends JEPA self-supervised learning to non-Euclidean geometries via local entropy maximization under geometric priors.

Bochner-Weitzenböck decomposition extended to cellular sheaf Laplacians with applications to curvature and neural diffusion models.

HypTI applies hyperbolic geometry to multimodal feature fusion for dementia detection from clinical and neuroimaging data.

Verification-guided training for neural Hamilton-Jacobi safety certificates uses probabilistic enumeration to detect forward-invariance violations and generate targeted counterexamples.

Neural decoder for error-correcting codes using discrete diffusion with certified optimality via LP relaxation and beam search.

Relay uses LLM agents to diagnose and reuse repairs for historical software build failures, recovering 69.7% of failing OSS-Fuzz cases.

Engram Memory Network improves prototype-based explainability by using neuroscience insights to encode task-relevant information like human memory.

2D CNN classifies hypnotic susceptibility from dense-array EEG during guided imagery on 62 participants.

AI labs have staked their reputations on model benchmarking — the supposedly neutral and accurate system of evaluations that are designed to measure whether one AI product is better than another. However, the methods behind these evaluations are complicated and still maturing, said Irene Solaiman, Hugging Face’s chief policy officer, during a discussion at TechCrunch […]

Amazon wants to break Nvidia’s hold on PyTorch, the free toolkit used to build most AI apps, so that more developers run their apps on alternative chips like its own.

Eugenia Kuyda's newest startup Wabi is positioned to take advantage of an idea she had more than a decade ago. Wabi offers a personal AI assistant with a twist, free and downloadable to anyone today.