# Active Imitation Learning for Thermal- and Kernel-Aware LFM Inference on 3D S-NUCA Many-Cores

arXiv: https://arxiv.org/abs/2604.11948 · HTML: https://mlsanity.com/paper/2604.11948/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 56 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Understanding and Robustifying Differentiable Architecture Search](https://mlsanity.com/paper/1909.09656/) (2019)
- [Optimizing CNN Model Inference on CPUs](https://mlsanity.com/paper/1809.02697/) (2018)
- [Efficient LLM Inference on CPUs](https://mlsanity.com/paper/2311.00502/) (2023)
- [Robustness of Large Language Models Against Adversarial Attacks](https://mlsanity.com/paper/2412.17011/) (2024)
- [A Novel Evaluation Framework for Image2Text Generation](https://mlsanity.com/paper/2408.01723/) (2024)
- [Gradient Weight-normalized Low-rank Projection for Efficient LLM Training](https://mlsanity.com/paper/2412.19616/) (2024)
- [AltGen: AI-Driven Alt Text Generation for Enhancing EPUB Accessibility](https://mlsanity.com/paper/2501.00113/) (2024)
- [SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation](https://mlsanity.com/paper/2502.05539/) (2025)
- [Inference Performance Optimization for Large Language Models on CPUs](https://mlsanity.com/paper/2407.07304/) (2024)
- [MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection](https://mlsanity.com/paper/2410.09103/) (2024)
- [Optimizing Numerical Estimation and Operational Efficiency in the Legal Domain through Large Language Models](https://mlsanity.com/paper/2407.19041/) (2024)
- [CoMeT: An Integrated Interval Thermal Simulation Toolchain for 2D, 2.5D, and 3D Processor-Memory Systems](https://mlsanity.com/paper/2109.12405/) (2021)
- [A Quantitative Analysis and Guidelines of Data Streaming Accelerator in Modern Intel Xeon Scalable Processors](https://mlsanity.com/paper/2305.02480/) (2023)
- [Energy-Efficient QoS-Aware Scheduling for S-NUCA Many-Cores](https://mlsanity.com/paper/2505.23351/) (2025)
- [Multi-Partner Project: COIN-3D -- Collaborative Innovation in 3D VLSI Reliability](https://mlsanity.com/paper/2601.14347/) (2026)

## Abstract (arXiv)

Large Foundation Model (LFM) inference is both memory- and compute-intensive, traditionally relying on GPUs. However, the limited availability and high cost have motivated the adoption of high-performance general-purpose CPUs, especially emerging 3D-stacked Static Non-Uniform Cache Architecture (3D S-NUCA) systems. These architectures offer enhanced bandwidth and locality but suffer from severe thermal challenges and uneven cache latencies due to 3D Networks-on-Chip (NoC). Optimal management of thread migration and V/f scaling is non-trivial due to LFM kernel diversity and system heterogeneity. Existing thermal management approaches often rely on oversimplified analytical models and lack adaptability. We propose AILFM, an Active Imitation Learning (AIL)-based scheduling framework that learns near-optimal thermal-aware scheduling policies from Oracle demonstrations with minimal run-time overhead. AILFM accounts for both core-level performance heterogeneity and kernel-specific behavior in LFMs to maintain thermal safety while maximizing performance. Extensive experiments show that AILFM outperforms state-of-the-art baselines and generalizes well across diverse LFM workloads.