The Archive

CUTS decoding strategy prevents mode collapse in GRPO on saturated reasoning benchmarks by enforcing structure-preserving exploration.

Multi-objective neural forecasting framework enforcing non-crossing prediction intervals via adaptive weight selection.

AI surrogate models trained on expert-validated CFD data accelerate race-car aerodynamic design exploration.

LQM hierarchical taxonomy diagnoses MT errors in diglossic languages beyond surface-form mistakes.

DPO-based alignment framework instills musical constraints in LLMs for lyric-to-melody generation without annotation.

Adversarial Humanities Benchmark tests robustness of frontier model safety refusals against stylistic prompt transformations.

OneVL compresses vision-language chain-of-thought reasoning into latent states for real-time autonomous driving.

Adaptive Conformal Filtering combines learned safety filters with conformal inference for high-dimensional control systems.

Pedagogical walkthrough of Physics-Informed Neural Network training cycle with explicit algebra and backpropagation.

WorldDB ontology-aware vector graph-of-worlds memory engine enables persistent long-horizon agent reasoning with typed edges.

MS-RCGR reversible multi-scale encoding transforms biological sequences into interpretable scale-invariant geometric features.

BAR framework trains domain-specific experts separately then composes via Mixture-of-Experts, avoiding catastrophic forgetting in multi-domain post-training.

NI Sampling optimizes token ordering in discrete diffusion LLMs to accelerate parallel decoding beyond heuristic step-selection baselines.

Generalized Synthetic Control Method improves baseline estimation for electricity demand response using causal inference; domain-specific, not core AI research.

Asset Harvester extracts 3D object assets from driving logs for closed-loop AV simulation, enabling agent manipulation and novel-view synthesis.

ConGA-PePPI and TC-PepGen integrate peptide-protein interaction prediction with target-conditioned generation; biotech application, not core LLM/AI architecture.

Extends Semantic Tube Prediction by sampling at reasoning step boundaries to improve geometric structure and efficiency in LLM fine-tuning.

DESPITE benchmark (12K tasks) reveals LLMs as robotic planners generate dangerous plans 28.3% of the time despite strong planning ability; scale ≠ safety.

Noetik applies autoregressive transformers (TARIO-2) to match cancer treatments with patients, targeting 95% clinical trial failure rate.

CmIR framework uses causal inference to disentangle invariant vs. spurious modality representations, improving multimodal robustness under distribution shift.

Online video understanding framework for streaming visual queries with decision transparency and evidence-aligned timing; addresses real-time constraints.

ESsEN trains compact vision-language transformers on small datasets for edge/robotic deployment, inspired by child language acquisition.

NSA is said to be using Anthropic's restricted Mythos AI model.

Random matrix theory analysis of gradient flow dynamics reveals transient learning regime driven by input covariance anisotropy before overfitting.

AutoPPA automates circuit PPA optimization by learning domain-specific rules via contrastive learning from RTL design patterns.

ProtoCLIP refines zero-shot chest X-ray classification by mitigating label co-occurrence bias and domain shift in CLIP models.

Robust conformal prediction method using half-mass radius non-conformity scores for distribution-free coverage under outliers and heavy tails.

Physics-informed neural ODEs coupled with DAE solvers enable scalable data-driven simulation of large HVAC systems.

Anthropic and Amazon expand partnership to secure up to 5 gigawatts of compute capacity for AI model development and deployment.

Qwen3-VL and Qwen models evaluated on Change VQA benchmark for temporal remote sensing image understanding with LoRA adaptation.