Research

Run a bounded standard-versus-chain-of-thought proxy recovery experiment and emit auditable recovery artifacts.

Compute Kernelized Stein Discrepancy pairwise Stein kernels and U/V-statistic estimates from samples, model scores, and an RBF kernel.

Run a bounded 1D Gaussian-mixture KSD-U recovery experiment for the Kernelized Stein Discrepancy paper.

Use this skill to compose PMD mixture protocol, KDE update, and density metrics modules into an executable bounded soft-mode recovery experiment with auditable evidence.

Minimise empirical Stein discrepancy objectives with bounded searches and auditable loss traces for recovery experiments.

Build continuous denoising score-matching targets, losses, and reduced optimizer evidence for Score SDE.

Validate reduced or full SBI recovery artifacts, source boundaries, mechanism checks, and metric reporting.

Run a bounded Gaussian/Gaussian SBI proxy recovery that exercises F-NPSE score training, composition, and sampling.

Run bounded SBI benchmark recovery from generated skills while enforcing source boundaries and validator-compatible evidence.

Run APT-style sequential simulator proposal rounds with auditable prior, proposal, observation, and update records for likelihood-free inference recovery.

Compose CoFi coarse and fine pruning masks and summarize active transformer structures for reduced recovery experiments.

Run a bounded CoFi proxy experiment that exercises masks, sparsity regularization, distillation, pruning summaries, and validation logs.

"Use Time-Series-Library (TSLib) to configure, run, debug, and

"Evaluate TensorRT SSD and YOLO object detectors on COCO-style bbox

"Evaluate SDGX real and synthetic tabular data with JSD,

"Prepare SDV demo data, local files, metadata, utilities, and logs

Keep Sacred runs reproducible and diagnose runtime capture/settings behavior.

"Install, configure, run, diagnose, and safely extend the

"Guides RoboVerse cross-simulator parity experiments, registration

"Guides Researchers through RoboCasa dataset registries, dataset

"Run and troubleshoot RD-Agent RL post-training and AutoRL-Bench

"Run and troubleshoot RD-Agent quantitative-finance factor and

"Operate Microsoft's RD-Agent research-agent framework for

"Use RAG-Retrieval for RAG reranker inference plus bundled