paper-with-me

홈 › Papers

Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search

2026-04-10 · Zhen Liu, Yuhan Liu, Jinjun Wang, Wei Song, Jianyi Liu, Jingwen Fu arxiv

This paper focuses on a key challenge in Neural Architecture Search (NAS): integrating established architectural knowledge while exploring new designs under expensive evaluations. Large language models (LLMs) are a promising assistant for NAS because they can translate rich architectural and coding priors into executable code edits. However, in practice, seemingly local revisions often propagate into non-local behavioral and performance shifts because a single edit can inadvertently couple multiple interacting functional factors, a phenomenon we refer to as functional entanglement. To make LLM knowledge usable under such entanglement, we propose Structured Progressive Knowledge Activation (SPARK), which activates relevant priors by explicitly selecting the functional factor to modify and conditioning the edit on that factor. This factor-conditioned editing reduces entangled side effects and yields more targeted, reliable architecture modifications. On CLRS-DFS, SPARK achieves a 28.1x sample-efficient architecture evolution speedup and yields a 22.9\% relative improvement in OOD accuracy. Our code is available at https://github.com/AIM-ResearchLab/SPARK.

📄 PDF Abstract BibTeX arXiv:2605.04057

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture Search

Similar Papers 제목 키워드 기반

Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling

2026-04-21 · Weijie Zhao, Mingquan Liu, Bolun Wang, Simo Wu 외 arxiv

Scaling Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learned representations. We identify the primary bottleneck in the attentio…

HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents

2026-04-18 · Jinchang Zhu, Jindong Li, Cheng Zhang, Jiahong Liu 외 arxiv

Long-term memory is a critical challenge for Large Language Model agents, as fixed context windows cannot preserve coherence across extended interactions. Existing memory systems represent conversation history as unstruc…

Semantic Similarity

Pretraining large language models with MXFP4 on Native FP4 Hardware

2026-05-11 · Musa Cim, Poovaiah Palangappa, Miro Hodak, Ravi Dwivedula 외 arxiv

Why does full-pipeline FP4 training of large language models often diverge, even when forward activations and activation gradients remain stable? We address this question through a controlled study of MXFP4 quantization …

Structured Knowledge Accumulation: An Autonomous Framework for Layer-Wise Entropy Reduction in Neural Learning

2025-03-18 · Bouarfa Mahi Quantiota

We introduce the Structured Knowledge Accumulation (SKA) framework, which reinterprets entropy as a dynamic, layer-wise measure of knowledge alignment in neural networks. Instead of relying on traditional gradient-based …

A Knowledge-Driven Diffusion Policy for End-to-End Autonomous Driving Based on Expert Routing

2025-09-05 · Chengkai Xu, Jiaqi Liu, Yicheng Guo, Peng Hang 외 arxiv

End-to-end autonomous driving remains constrained by the difficulty of producing adaptive, robust, and interpretable decision-making across diverse scenarios. Existing methods often collapse diverse driving behaviors, la…

Autonomous Driving