DIFFNAS: Predictor-Free Neural Architecture Search via Diffusion Model and Zero-Cost Evaluation
cs.LG
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/D-X-Y/NAS-Bench-201
Terminology
Sources
- Multi-conditioned Graph Diffusion for Neural Architecture Search
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
- NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search
- Scalable Diffusion Models with Transformers
- CAP: A Context-Aware Neural Predictor for NAS
- Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
- Generative Diffusion Models on Graphs: Methods and Applications
- DARTS: Differentiable Architecture Search
- Fine-Grained Visual Classification of Aircraft
- TG-NAS: Generalizable Zero-Cost Proxies with Operator Description Embedding and Graph Learning for Efficient Neural Architecture Search
- DiGress: Discrete Denoising diffusion for graph generation
- PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
- Neural Architecture Search with Reinforcement Learning
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning