The Archive

Fisher geometry analysis reveals safety alignment fragility in LLMs under benign fine-tuning via selective output-side MLP resharpening.

Empirical study comparing expert and imitation-learned dexterous manipulation policies across task execution speeds.

Timestep-free diffusion denoiser with persistent hidden state enables anytime reasoning, achieving 99.90% on Sudoku-Extreme.

Amazon is adding a new Alexa-powered feature called “Update Me When” that can send personalized alerts about product launches, tours, books, shows, and other events that could trigger a purchase.

Edge-girth structural descriptor for GNNs addresses Weisfeiler-Leman limitations without precommitting to subgraph size.

AIR's platform can discover agents running at a company, continuously vets any skills and add-ons they use, and blocks any unwanted behaviour.

HarnessDev benchmark evaluates LLM agents on infrastructure generation, shifting evaluation from task outputs to runnable code.

Masked-citation study shows LLMs cite less critically and with weaker rhetorical intent than human-generated scientific citations.

Power-Law Entropy Search (PLES) uses multi-fidelity Bayesian optimization to efficiently estimate optimal LLM hyperparameter scaling laws.

TREVIS: Tree Transformer VAE approach jointly optimizes decision tree predictive performance and structural sparsity.

TRIAGE three-level routing framework reduces LLM agent token consumption by reusing historical trajectories as reusable skills.

Vision Transformer method for cancer grading combines nuclei classification with histopathology images via semantic-guided multimodal preprocessing.

CATeye framework detects e-commerce voucher fraud by learning invariances across attribute-topology distribution shifts without retraining.

Self-Routing post-training framework routes LLM samples to GRPO, distillation, or regularization based on rollout correctness without external teachers.

Provably safe sim-to-real RL transfer method addresses simulator-reality mismatch with safety guarantees for robotics and healthcare applications.

Physics-Informed Neural Networks applied to Ground-Penetrating Radar data prediction for subsurface anomaly forecasting.

Wasserstein-based analysis of generative data augmentation shows risk distortion controlled by augmentation strength and class-conditional distribution discrepancy.

datasette-mcp 0.2 releases with structured SQL result format (objects instead of arrays) to improve weaker model reasoning over tabular data.

DaEdiTikZ dataset leverages scientific revision trajectories to train VLMs for iterative scientific figure editing without synthetic supervision.

NeuSOGA framework extracts explicit symbolic mathematical representations from geometric observations using neuro-symbolic learning.

Contribution-aware bandwidth allocation optimizes split learning for multimodal edge training by allocating uplink budget based on modality importance.

DroneCATS benchmark evaluates MLLMs as generalist vision-language-action agents for drone control with full action-space prompting.

Fambot is building an AI “chief of staff” to help families manage the emails, calendars, school updates, sports schedules, and other logistics of raising kids.

The surge in AI adoption is transforming everything from chatbots to content generation. Still, a common pain point remains: How can organizations confidently... The surge in AI adoption is transforming everything from chatbots to content generation. Still, a common pain point remains: How can organizations confidently size GPU resources for inference workloads and optimize Total Cost of Ownership (TCO)? With a dizzying mix of latency targets, model choices, quirky traffic patterns, and budget constraints, it’s easy to feel lost in the weeds… Source

Python 3.15.0 RC2 released; final version due October with only bugfix changes permitted.

Nvidia is officially launching DLSS 5 this week, following a divisive announcement in March where we likened the AI upscaling tech to a "real-time generative AI filter for video games" and "motion smoothing for video games, but worse." DLSS 5 will officially be available on RTX 50-series desktop and laptop GPUs and through GeForce Now cloud gaming, though the only game with the tech so far is NBA 2K27 - which is launching September 3rd at 9PM PT on PC. When it was announced, Nvidia lauded DLSS 5 as "the company's most significant breakthrough in computer graphics since the debut of real-time ...

OpenAI's Astra model achieves Critical cybersecurity capability threshold under Preparedness Framework, introducing enhanced safeguards for deployment.

Systematic ablation study identifies four design principles for robust visual text representation learning in pixel space across variable resolutions and languages.

Deep learning approach to stain normalization in medical imaging reduces color variation artifacts for diagnostic systems.

Celeb Twins Test Set (CTTS) benchmark for monozygotic twin face verification with metadata for distinguishing marks and asymmetry.