arXiv Machine Learning
Jul 9
LEMUR 2: Unlocking Neural Network Diversity for AI
arXiv:2607. 06839v1 Announce Type: new Abstract: Existing NAS benchmarks (e.
GraphIR: Architecture-Level Search States for LLM-Guided Neural Architecture Evolution
arXiv:2608. 01633v1 Announce Type: new Abstract: Large language models (LLMs) enable neural architecture search (NAS) directly over executable neural network programs.
Related stories
arXiv Machine Learning
Jul 8
Leveraging Neural Graph Compilers in Machine Learning Research for Edge-Cloud Systems
arXiv:2504. 20198v2 Announce Type: replace-cross Abstract: This work presents a comprehensive evaluation of neural network graph compilers across heterogeneous hardware platforms, addressing the critical gap between theoretical optimization techniques and practical deployment scenarios.
arXiv Computation and Language
Sep 10
$\Phi$-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?
arXiv:2609.10226v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the prospect that they could assist in...
arXiv AI
Jun 30
Scalable Synthesis of distributed LLM workloads through Symbolic Tensor Graphs
arXiv:2511. 10480v3 Announce Type: replace-cross Abstract: Optimizing the performance of large language models (LLMs) on large-scale AI training and inference systems requires a scalable and expressive mechanism to model distributed workload execution.
arXiv AI
Aug 21
Repo0: Design-Driven Zero-to-All Code Generation
arXiv:2608. 19854v1 Announce Type: cross Abstract: Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture.
arXiv AI
Jul 3
Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation
arXiv:2607. 01590v1 Announce Type: new Abstract: Developing high-performance kernels for Neural Processing Units (NPUs) is a critical industry bottleneck, requiring developers to manually navigate implicit hardware constraints and strict memory hierarchies.
arXiv AI
Sep 2
CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language
CUDA‑Harness is a framework that enables the generation and optimization of CUDA kernels directly from natural language. It introduces Intermediate‑Structured Generation to bridge high‑level semantics with low‑level kernel code, uses Synthesis‑Based Verification to mitigate reward hacking by providing isolated test data, and employs Feedback‑Adaptive Evolution to prioritize correctness while improving performance. Experiments show the approach generalizes across different large language models, hardware platforms, and even supports C‑to‑CUDA transpilation.
arXiv AI
Jul 1
Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search
arXiv:2605. 04057v3 Announce Type: replace-cross Abstract: This paper focuses on a key challenge in Neural Architecture Search (NAS): integrating established architectural knowledge while exploring new designs under expensive evaluations.
arXiv Machine Learning
Aug 4
Nova: An End-to-End MLIR Compiler for Deep Learning
arXiv:2608. 00029v1 Announce Type: cross Abstract: The performance of deep learning models at scale relies heavily on how effectively high-level mathematical operations are mapped to underlying physical hardware.
arXiv Machine Learning
Aug 27
ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures
ONNX-Net introduces a universal representation for neural architectures using natural language descriptions, enabling instant performance prediction across diverse search spaces. The authors present ONNX-Bench, a benchmark of over 600k architecture–accuracy pairs compiled from open‑source NAS‑bench networks in ONNX format. Experiments demonstrate strong zero‑shot predictive performance with minimal pretraining, overcoming the limitations of cell‑based, graph‑encoded approaches.
arXiv AI
Jun 26
EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
arXiv:2606. 26578v1 Announce Type: new Abstract: Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges.
arXiv AI
Jun 9
Seq103: A Unified Neuroevolution Framework for Compact Sequence Architecture Discovery
arXiv:2606. 07664v1 Announce Type: cross Abstract: Neuroevolution is a representative neural architecture search paradigm that evolves both network topology and weights through evolutionary algorithms.