From Experience to Expertise: Adoption-Aware Memory Learning for Data-Scarce NPU Kernel Synthesis
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/anomalyco/opencode
Sources
- Towards Automated Kernel Generation in the Era of LLMs
- CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
- AgenticCANN: Automated Ascend C Operator Generation via Knowledge-Augmented Agentic Evolution
- KernelBench: Can LLMs Write Efficient GPU Kernels?
- Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis
- AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units
- AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization
- Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
- MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
- MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
- CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization
- Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
- NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation
- AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation
- Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation
- From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
- MemGPT: Towards LLMs as Operating Systems
- Qwen3-Coder-Next Technical Report
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks