Machine learning

Audits any landing or service page across 48 checks in 10 categories for LLM/AI discoverability, GEO readiness, content clarity, schema markup, internal…

State-space model with O(n) complexity vs Transformers' O(n²).

Generate AI videos using ByteDance Seedance models via Volcengine Ark API.

Author a new ShapeShifter graph-transformation pass for AMD Quark (ONNX or PyTorch).

End-to-end Quark ONNX AutoSearchPro recipe — drives `quark.onnx.AutoSearchPro` (Optuna-based hyperparameter search) on a `.onnx` model to find the best…

End-to-end ONNX PTQ workflow for AMD Quark — for `.onnx` input models (with optional sibling `.onnx_data` external-weights file).

Apply existing ShapeShifter graph passes to an .onnx model via the quark-cli shapeshifter CLI or a ShapeShifter YAML.

Install or verify the correct PyTorch build for a user's accelerator backend before Quark installation.

End-to-end LLM accuracy evaluation on AMD ROCm (ROCm-only) — docker container setup OR host (no-docker) runtime, vLLM/SGLang/ATOM serving, lm-eval / lighteval…

Inspect a HuggingFace transformers / safetensors model and prepare metadata for Quark Torch PTQ planning.

Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan…

Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.

Validate Quark Torch quantization output (HuggingFace safetensors + config.json) using four lightweight checks: auxiliary file copy alignment, excluded tensor…

Shrink a HuggingFace safetensors model to 1 hidden layer for fast debugging without loading the full model into memory.

Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures…

Use Hugging Face Hub via MCP server tools.

Build, maintain, and query a personal LLM-managed wiki — a markdown knowledge base where the LLM owns all writing, cross-referencing, and bookkeeping while…

Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG)…

Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model.

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's…

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance…

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream…

Meta's 7-8B specialized moderation model for LLM input/output filtering.

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML…