Results for “accuracy”

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Registers as a trading agent on zHive, fetches crypto signals, posts predictions with conviction, and competes for accuracy rewards.

Quantize large language models to 4-bit precision using activation-aware weight quantization, reducing memory footprint and speeding up inference with minimal accuracy loss.

Rates an agent's own output on five axes — accuracy, completeness, clarity, actionability, conciseness — producing a structured scorecard with evidence and improvement suggestions.

Use `task-agent` to update source-backed documentation or `review-agent` to assess documentation impact and accuracy when public behavior or operator workflows change. Skip work with no audience-facing behavior change.

Quantize large language models to 4-bit using activation-aware weight quantization, achieving ~3x speedup with minimal accuracy loss for deployment on limited GPU memory.

Evaluates text-to-image models on spatial relationship accuracy using the VISOR metric, separating object detection from spatial correctness to reveal biases like object priority and merging.

Review the week using accumulated session evidence — retrieval rates, hint depths, calibration accuracy, transfer and unassisted results. The learner identifies patterns and sets a strategy goal. Use weekly or after a multi-session period.

Reconciles project documentation, agent memory, and rule files against the actual codebase after a development session, ensuring accuracy and consistency across all knowledge layers.

Transcribe audio with high accuracy using ElevenLabs Scribe models, supporting speaker diarization, audio event tagging, forced alignment, and subtitle generation via the inference.sh CLI.

Managing privacy risks from AI-driven inferences about individuals including derived data classification, profiling under GDPR Art. 22, inference accuracy obligations, and controlling automated personality/behaviour predictions. Keywords: AI inference, derived data, profiling, automated predictions, GDPR.

Quantifies the minimum accuracy gap needed between two models for a sampled micro-benchmark to reliably preserve their ranking, using the MDAD metric from Yauney et al. (2025).

Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.

Improves AI skills for activation, clarity, and cross-model reliability through benchmarking, salience tuning, and regression triage.

Evaluates the correlation between automatic text generation scores and human quality ratings, including robustness to domain and quality drift, using metrics like Kendall's Tau and Pearson correlation.

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.

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines

Capture confidence ratings before and after a learning attempt to identify overconfidence and underconfidence patterns. Use when a student wants to understand how well they actually know something versus how well they think they know it.

Computes the SQuAD metric using torchmetrics, given predictions and ground truth. Use when evaluating question-answering outputs with exact match and F1 scores.

Benchmarks long-context language models across 20 sub-tasks spanning 3k–200k tokens, covering retrieval, reasoning, summarization, and instruction understanding, with exact-match accuracy as the primary metric.

Compress large language models by 40-60% with minimal accuracy loss using one-shot pruning techniques like Wanda and SparseGPT, enabling faster inference and deployment on constrained hardware.

Evaluates geometric consistency in text-to-video generation by measuring structural and motion coherence across camera trajectories, detecting deformation and occlusion artifacts in static scenes.

Computes CIDEr and related metrics to score how well generated image descriptions align with human consensus, using reference sentences and triplet annotations.

Fine-tune LLMs using LoRA, QLoRA, and PEFT with Hugging Face, including dataset preparation, hyperparameter tuning, evaluation, and deployment.

Pre-ingestion verification for epistemic quality in RAG systems with 9-point verification and Two-Round HITL workflow

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Benchmarks automatic post-editing (APE) models on WMT'18 SMT, SubEdits, and MLQE-PE datasets, reporting BLEU, ChrF, and TER scores computed with SacreBLEU and TERCOM.

Measures whether coding agents actually follow skills, rules, or agent definitions by generating test scenarios, running agents, and classifying tool calls to report compliance rates.

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.