Kernel Contracts is a specification language that formalizes correctness requirements for ML kernels to ensure consistent results across heterogeneous silicon platforms.
InProceedings of the Fif- teenth ACM International Conference on Web Search and Data Mining, WSDM ’22, pages 1256–1265, New York, NY , USA
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 9roles
background 1polarities
background 1representative citing papers
PrecisionDiff is a differential testing framework that uncovers widespread precision-induced behavioral disagreements in aligned LLMs, including safety-critical jailbreak divergences across precision formats.
Extends vLLM with delay-pattern de-interleaving, multi-stream sampling, and co-scheduled CFG to achieve 80% of non-CFG throughput for unified audio tasks while open-sourcing the pipeline.
vla.cpp is a unified C++ runtime that serves multiple VLA architectures with flow-matching and diffusion patterns, matching SOTA performance on LIBERO while running on low-memory embedded hardware.
Paraphrase Jaccard similarity of 0.135-0.288 falls below the 0.50-0.61 same-prompt rerun baseline on OpenAI and Anthropic models, showing prompt wording dominates buyer intent in commercial recommendations.
MarginGate triggers verification only on low-margin decode steps to achieve 100% deterministic batch inference at 15-50% of the cost of always-on verification across tested models and datasets.
Financial AI systems using tabular models, graph networks, and LLM agents exhibit nondeterminism that undermines reproducibility, quantified via experiments on public datasets and addressed by a proposed layered evaluation framework linking metrics to audit readiness.
A 21-configuration LLM judge ensemble (7 models × 3 prompts) validates synthetic e-commerce attribute labels at 95.2% agreement with human experts across 4 languages and 12,726 products.
Case study applies verifier-guided LLM evolutionary agents to contraction-order optimization in tensor networks and concludes that human validation remains essential.
citing papers explorer
-
Kernel Contracts: A Specification Language for ML Kernel Correctness Across Heterogeneous Silicon
Kernel Contracts is a specification language that formalizes correctness requirements for ML kernels to ensure consistent results across heterogeneous silicon platforms.
-
Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements
PrecisionDiff is a differential testing framework that uncovers widespread precision-induced behavioral disagreements in aligned LLMs, including safety-critical jailbreak divergences across precision formats.
-
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
Extends vLLM with delay-pattern de-interleaving, multi-stream sampling, and co-scheduled CFG to achieve 80% of non-CFG throughput for unified audio tasks while open-sourcing the pipeline.
-
vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models
vla.cpp is a unified C++ runtime that serves multiple VLA architectures with flow-matching and diffusion patterns, matching SOTA performance on LIBERO while running on low-memory embedded hardware.
-
Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline
Paraphrase Jaccard similarity of 0.135-0.288 falls below the 0.50-0.61 same-prompt rerun baseline on OpenAI and Anthropic models, showing prompt wording dominates buyer intent in commercial recommendations.
-
MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference
MarginGate triggers verification only on low-margin decode steps to achieve 100% deterministic batch inference at 15-50% of the cost of always-on verification across tested models and datasets.
-
From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems
Financial AI systems using tabular models, graph networks, and LLM agents exhibit nondeterminism that undermines reproducibility, quantified via experiments on public datasets and addressed by a proposed layered evaluation framework linking metrics to audit readiness.
-
SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation
A 21-configuration LLM judge ensemble (7 models × 3 prompts) validates synthetic e-commerce attribute labels at 95.2% agreement with human experts across 4 languages and 12,726 products.
-
Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks
Case study applies verifier-guided LLM evolutionary agents to contraction-order optimization in tensor networks and concludes that human validation remains essential.