The Archive

Twin-world credit assignment isolates policy decisions from random sampling noise in episodic reinforcement learning with deterministic components.

Microsoft points the blame for ConnectWise's breach at a China-aligned hacker, which relied on AI agents to rapidly hack into thousands of its customers.

PYTHIA framework applies transfer learning and foundation models to material defect and adsorption site optimization with reduced sample requirements.

LACToS method for localized anomaly detection in images, handling multimodal in-distribution data beyond industrial defect contexts.

GPU applications are processing ever-growing datasets with increasingly powerful accelerators. According to the 2025 Stanford AI Index, compute for notable AI... GPU applications are processing ever-growing datasets with increasingly powerful accelerators. According to the 2025 Stanford AI Index, compute for notable AI models has been doubling approximately every five months, while the size of datasets used to train LLMs has been doubling approximately every eight months. As computation and data scale together, moving data efficiently from storage becomes… Source

Empirical benchmark of recent LLMs vs. fine-tuned encoder-decoder models on knowledge-graph-to-text generation, narrowing performance gap.

Diona regression method estimates state derivatives at query points with admissible bounds via local constrained optimization instead of global training.

Autoregressive factorization with parallel gradient boosting for nonparametric high-dimensional probability distribution estimation.

Autoregressive models can leak future tokens during training via architectural bugs, artificially inflating eval metrics while harming generation quality.

Framework for continual learning from user corrections in interactive systems via typed feedback interfaces.

Mechanistic interpretability reveals causal subspaces controlling metaphor representation in LLMs across architectures.

Production case study: moving compliance rules from prompts to structured retrieval context improves LLM pharmaceutical claims generation.

User simulators balancing complex intent adherence with natural conversational behavior for multi-turn AI assistant evaluation.

Overcooked-inspired benchmark for evaluating vision-language agent coordination on multi-player task planning in Unreal Engine.

Music generation method expands piano MIDI to pop production via flow-matching without paired piano-pop training data.

Neuro-symbolic household food recommender balancing dietary constraints and fairness via constrained fair division.

Physics-informed reduced-order models for thin panel dynamics in supersonic/hypersonic flow using Ritz-Galerkin methods.

Wildwood is the most ambitious film yet from Laika, the stop-motion studio best known for the likes of Coraline and ParaNorman. It's a sprawling fantasy adventure that took five years to complete. The process involved more 230 puppets - including 36 of the main character Prue alone - which were brought to life by a team of 49 animators. All told, more than 1,000 artists worked on the film in some form. The painstaking process that goes into making a Laika film offers a distinct counterpoint to the instant progress promised by generative AI tools. Recently Wildwood director and Laika CEO Travi...

Bayesian optimization method for high-dimensional latent spaces using affine surrogates with limited evaluation budgets.

Small open-weight LLM trained via RL to select tools from corpora of 10k+, matching proprietary model performance on ToolBench.

Empirical evaluation of LLM inference optimizations (KV-cache pruning, speculative decoding, quantization) on Apple Silicon vs NVIDIA GPUs.

Motion-guided VLM for efficient video anomaly detection using temporal gradient magnitude to trigger inference only when needed.

The ride share giant previously deployed a much smaller pilot for ChatGPT Work, but is now taking the enterprise agent company-wide.

AI developers aren’t just running a single model anymore—they’re orchestrating multiple models in parallel, chaining inference calls, and experimenting... AI developers aren’t just running a single model anymore—they’re orchestrating multiple models in parallel, chaining inference calls, and experimenting with frontier-class architectures that demand hundreds of gigabytes of memory. NVIDIA DGX Spark was built to bring AI development to the desk, and now you’ll be able to link even more Spark nodes together. At GTC Berlin… Source

Study reveals ASR systems miss 22-42% of rare words in human speech, inflating measured TTS error rates by 2-3x on evaluation benchmarks.

LLM-based framework for translating structured clinical data into patient-readable health narratives while preserving clinical semantics.

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

Framework for coding agents to dynamically select skill granularity (primitive/macro/hybrid) at runtime, enabling fallback recovery strategies.

Dialog system using perspectivized stance vectors instead of scalar scores to select appropriately distant viewpoints for user engagement.