The Archive

RadiomicNet combines handcrafted radiomics features with deep learning for interpretable medical image segmentation.

Microsoft follows Amazon, OpenAI and Anthropic with its new AI deployment group.

DALorRA applies Bayesian sparse low-rank adaptation to quantify LLM uncertainty and reduce overconfidence in fine-tuned models.

Rubric-based clinical reasoning benchmark shows frontier LLMs achieve ~32% on hard expert-authored medical cases.

Dynamic Neural Graph Encoding uses temporal graphs to analyze neural network weight spaces and inference sequences.

Proves multi-secretary problem requires Ω((log T)²) regret for bounded-density distributions with support gaps.

Ensemble machine learning methods detect early-stage Alzheimer's disease biomarkers from neural network analysis.

A²utoLPBench auto-generates infinite linear programming word problems via inverse-KKT for LLM-agent evaluation.

Probes chemical language models across eight pre-trained variants to identify which molecular substructures are encoded.

ART learns adaptive timestep schedules for diffusion sampling via continuous-time control and actor-critic optimization.

Paper-replication workflow enables coding agents to verify computational claims in scientific ML papers with recorded evidence and automated verification.

AbsoluteDegradation introduces physics-based synthetic film degradation pipeline and benchmark for archival film restoration without paired training data.

Deep learning model for automated population-scale penile tissue segmentation in MRI to enable quantitative male reproductive health phenotyping.

Rolling Split Conformal Prediction framework for pre-incident traction loss detection via tire slip monitoring in vehicle safety systems.

Behavioral monitoring technique to distinguish guardrail blocks from LLM rejections in black-box adversarial evaluation of production systems.

vLLM-based inference pipeline for unified audio understanding and generation with native support for multi-token prediction and delay-pattern interleaving.

FitOne domain-specialized LLM (8B/32B) improves scientific fitness coaching reliability through domain-specific post-training.

Artificial intelligence may have captured the public imagination through chatbots and image generators, but some of its most consequential use cases are unfolding far from consumer-facing tools. In industries where physical infrastructure, operational continuity, and safety are paramount, AI is becoming a core operating layer. With its sprawling industrial systems and constant stream of operational…

ContextNest open specification for verifiable context governance in autonomous AI agents with provenance, version control, and integrity guarantees.

Bias-aware Bayesian active ranking framework identifies top-k items under fixed budget while mitigating systematic biases in LLM judge comparisons.

Structured Gaussian process classifier integrates biological pathway graphs into kernel design for high-dimensional omics classification with uncertainty quantification.

WBMM optimizes large-kernel convolutions via windowed batching and regular memory access, improving efficiency on large feature maps.

Guided Action Flow enables test-time guidance of frozen SmolVLA policies using learned action-chunk critics for robot manipulation.

Improved Fourier Neural Operators for Rayleigh-Bénard convection via time-increment prediction achieve faster inference with 314k parameters.

SUNTA uses prediction-error-driven chunking in hierarchical state-space models for improved long-horizon video prediction.

Evolutionary Wave Function Collapse combines procedural content generation with evolutionary search over small input examples for level generation.

HaloGuard 1.0 releases open-weights constitutional safety classifier achieving state-of-the-art multilingual prompt-safety performance at 1/10 model size.

Maven framework adds evidence-state value functions to long-context RL, rewarding intermediate reasoning transitions for improved synthesis.

kNNGuard provides training-free LLM guardrails via multi-layer kNN over hidden activations, requiring only 50 labeled examples.

ADTC formalizes exhaustive analysis of decision trees via algebraic model counting for explainability verification.