Results for “cross-functional-alignment”

Guide cross-functional teams through creating Jeff Gothelf's Lean UX Canvas v2 to frame business problems, surface assumptions, and define experiments.

Alignment

Use when performing multiple sequence alignment of FASTA inputs, generating alignment ensembles, or calculating alignment confidence metrics.

Fine-tune Cosmos Reason video QA models using supervised fine-tuning with FSDP parallelism, including dataset preparation, spec construction, and AutoML support.

Use when masking columns or coordinate ranges in multiple-sequence alignments before downstream HMMER or alignment-processing steps.

Use when performing multiple sequence alignment on nucleotide or protein sequences, such as preparing alignments for phylogenetic analysis or comparative genomics.

当寻求个人行动或项目在更宏大系统中的意义，或需要将日常工作与长远价值连接时

Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.

Scale alignment for RNA-protein cross-modal integration - BOTH modalities must be z-scored

Provides a structured reasoning protocol for diagnosing complex relationships, organizations, institutions, public disputes, or long-term evolution using the CrossFrame framework, with explicit invocation required.

Use when performing multiple sequence alignments on protein or nucleotide sequences, generating phylogenetic trees, or producing alignment output in various formats.

当设定新目标或检视现有目标时，确保目标能通过高效的行为系统自动达成

Spatial region-aware cell matching for CODEX/scRNAseq integration

Evaluates automated metrics and vision-language models on identifying granular errors in detailed image descriptions and ranking paired descriptions against human judgments, using macro F1, pairwise accuracy, Spearman rank ρ, and Kendall's τ.

Applies TRIZ cross-domain analogical reasoning to find solutions from adjacent fields. Use when stuck on a problem and needing inventive perspectives.

Scores generated image captions against reference captions and source images using the Polos metric, which is trained to align with human judgments and probes hallucination robustness and open-vocabulary evaluation.

Cardinality and model family jointly determine the encoding.

COCO: Microsoft COCO: Common Objects in Context

Pixtral 12B: A Frontier Multimodal Model

Kinetics-400: A Large Video Understanding Dataset

Pose-conditioned generation on RunComfy via the `runcomfy` CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion / blocking of a reference video onto a target character), community Wan 2-2 Animate (audio-driven character animation with pose conditioning), and Z-Image Turbo ControlNet LoRA (pose-conditioned image generation from an OpenPose / DWPose / canny / depth control image). Picks the right route based on video vs still and stylized vs photoreal. Triggers on "controlnet", "control net", "pose control", "openpose", "DWPose", "transfer pose", "motion control", "pose driven", "character pose", "depth control", "canny edge", "use this pose", or any explicit ask to condition generation on a pose / skeleton / motion / depth / canny reference.

CogVLM: Visual Expert for Pretrained Language Models

Reverse-engineers a federal RFP we received — given the SOW/PWS and evaluation criteria already in the Theseus KG, reconstructs the CO's hidden decision tree (upstream `sow-pws-builder` 6 scope blocks + 3 intake answers), surfaces hot buttons, ghost language, discriminator hooks, missing-section signals, and CPFF-form / Section-5 / QASP / Key-Personnel traps. USE WHEN the user asks "what scope decisions did the CO already make?", "reverse engineer this RFP", "what hot buttons are hiding in this PWS?", "where are the discriminator hooks?", "did they pick CPFF completion or term form?", "anything suspiciously missing?", or any variant of decoding CO intent. Pulls `requirement`, `deliverable`, `proposal_instruction`, `evaluation_factor`, `clause`, `performance_standard` from the active workspace KG and emits a JSON envelope feeding `proposal-generator`. DO NOT USE FOR proposal prose (`proposal-generator`), pricing (`price-to-win`), clause audit (`compliance-auditor`), or sub SOW (`subcontractor-sow-builder`).

Mantis: Interleaved Multi-Image Instruction Tuning

Perform fast genomic interval operations (overlap, nearest, merge, coverage, cluster, complement, subtract, count-overlaps), multi-format bioinformatics I/O, DataFusion SQL, and pileup on Polars DataFrames via the polars-bio library, serving as a scalable alternative to bioframe and bedtools.

Task Decomposition

Specialist orchestrating codex exec / Antigravity CLI through dual paradigms — COMPETE (multi-variant comparison, select best) and COLLABORATE (decompose tasks across engines, integrate). Supports Solo/Team/Quick execution modes.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Evaluates the robustness and alignment with human judgment of reference-based and reference-free evaluation metrics for machine translation and summarization, particularly under adversarial conditions.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Use when aligning RNA-seq reads to a reference genome using graph-based indexing for fast and sensitive spliced alignment.

Quick feasibility and novelty check — go/no-go decision for this week's build

Mathematical AI interpretability with sheaf cohomology, spectral analysis, causal inference, and hallucination prevention

Composite skill — safely refactor a module end-to-end with sequencing, parallel implementation, post-refactor cleanup, and rationale capture. Chains refactor-plan (phased plan + rollback) → three-man-team (architect/builder/reviewer in parallel) → fix-the-suite post-refactor → adr-write → docs-sync. Use for non-trivial refactors that need both careful sequencing and durable record.