We study in-context learning for nonparametric regression with $α$-Hölder smooth regression functions, for some $α>0$. We prove that, with $n$ in-context examples and $d$-dimensional regression covariates, a pretrained transformer with $Θ(\log n)$ parameters and $Ω\bigl(n^{2α/(2α+d)}\log^3 n\bigr)$ pretraining sequences can achieve the minimax-optimal rate of convergence $O\bigl(n^{-2α/(2α+d)}\bigr)$ in mean squared error. Our result requires substantially fewer transformer parameters and pretraining sequences than previous results in the literature. This is achieved by showing that transformers are able to approximate local polynomial estimators efficiently by implementing a kernel-weighted polynomial basis and then running gradient descent.

Feedforward networks (FFN) are ubiquitous structures in neural systems and have been studied to understand mechanisms of reliable signal and information transmission. In many FFNs, neurons in one layer have intrinsic properties that are distinct from those in their pre-/postsynaptic layers, but how this affects network-level information processing remains unexplored. Here we show that layer-to-layer heterogeneity arising from lamina-specific cellular properties facilitates signal and information transmission in FFNs. Specifically, we found that signal transformations, made by each layer of neurons on an input-driven spike signal, demodulate signal distortions introduced by preceding layers. This mechanism boosts information transfer carried by a propagating spike signal, and thereby supports reliable spike signal and information transmission in a deep FFN. Our study suggests that distinct cell types in neural circuits, performing different computational functions, facilitate information processing on the whole.

We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While multi-head mechanisms enhance expressivity in attention, naively applying them to FFNs faces two challenges: memory consumption scaling with the head count, and an imbalanced ratio between the growing intermediate size and the fixed head dimension as models scale, which degrades scalability and expressive power. To address these challenges, we propose Flash Multi-Head FFN (FlashMHF), with two key innovations: an I/O-aware fused kernel computing outputs online in SRAM akin to FlashAttention, and a design using dynamically weighted parallel sub-networks to maintain a balanced ratio between intermediate and head dimensions. Validated on models from 128M to 1.3B parameters, FlashMHF consistently improves perplexity and downstream task accuracy over SwiGLU FFNs, while reducing peak memory usage by 3-5x and accelerating inference by up to 1.08x. Our work establishes the multi-head design as a superior architectural principle for FFNs, presenting FlashMHF as a powerful, efficient, and scalable alternative to FFNs in Transformers.

Diffusion models deliver high-fidelity synthesis but remain slow due to iterative sampling. We empirically observe there exists feature invariance in deterministic sampling, and present InvarDiff, a training-free acceleration method that exploits the relative temporal invariance across timestep-scale and layer-scale. From a few deterministic runs, we compute a per-timestep, per-layer, per-module binary cache plan matrix and use a re-sampling correction to avoid drift when consecutive caches occur. Using quantile-based change metrics, this matrix specifies which module at which step is reused rather than recomputed. The same invariance criterion is applied at the step scale to enable cross-timestep caching, deciding whether an entire step can reuse cached results. During inference, InvarDiff performs step-first and layer-wise caching guided by this matrix. When applied to DiT and FLUX, our approach reduces redundant compute while preserving fidelity. Experiments show that InvarDiff achieves $2$-$3\times$ end-to-end speed-ups with minimal impact on standard quality metrics. Qualitatively, we observe almost no degradation in visual quality compared with full computations.

Transformer-based models have gained considerable attention in the field of physiological signal analysis. They leverage long-range dependencies and complex patterns in temporal signals, allowing them to achieve performance superior to traditional RNN and CNN models. However, they require high computational intensity and memory demands. In this work, we present Efficient-Husformer, a novel Transformer-based architecture developed with hyperparameter optimization (HPO) for multi-class stress detection across two multimodal physiological datasets (WESAD and CogLoad). The main contributions of this work are: (1) the design of a structured search space, targeting effective hyperparameter optimization; (2) a comprehensive ablation study evaluating the impact of architectural decisions; (3) consistent performance improvements over the original Husformer, with the best configuration achieving an accuracy of 88.41 and 92.61 (improvements of 13.83% and 6.98%) on WESAD and CogLoad datasets, respectively. The best-performing configuration is achieved with the (L + dm) or (L + FFN) modality combinations, using a single layer, 3 attention heads, a model dimension of 18/30, and FFN dimension of 120/30, resulting in a compact model with only about 30k parameters.

Vision Transformers (ViTs) have demonstrated remarkable performance across a range of computer vision tasks; however, their high computational, memory, and energy demands hinder deployment on resource-constrained platforms. In this paper, we propose \emph{Cascaded-ViT (CViT)}, a lightweight and compute-efficient vision transformer architecture featuring a novel feedforward network design called \emph{Cascaded-Chunk Feed Forward Network (CCFFN)}. By splitting input features, CCFFN improves parameter and FLOP efficiency without sacrificing accuracy. Experiments on ImageNet-1K show that our \emph{CViT-XL} model achieves 75.5\% Top-1 accuracy while reducing FLOPs by 15\% and energy consumption by 3.3\% compared to EfficientViT-M5. Across various model sizes, the CViT family consistently exhibits the lowest energy consumption, making it suitable for deployment on battery-constrained devices such as mobile phones and drones. Furthermore, when evaluated using a new metric called \emph{Accuracy-Per-FLOP (APF)}, which quantifies compute efficiency relative to accuracy, CViT models consistently achieve top-ranking efficiency. Particularly, CViT-L is 2.2\% more accurate than EfficientViT-M2 while having comparable APF scores.

When training deep neural networks, a model's generalization error is often observed to follow a power scaling law dependent both on the model size and the

A.1 Proof of Equation 9 We prove Eq. 9 by contradiction. Due to the observation (2) in Section 4.1, the following inequalities hold: X Algorithm 2 is our proposed algorithm for latency-aware mask search, which extends Algorithm 1. Based on Eq. 5 and the warm-start constraint in Section 4.2, the optimization problem Eq. 4 is written If there exists a mask m that strictly better optimizes Eq. 22 than ˆ m: Although Eq. 27 has a closed form B, we use the numerical solver in CuPy for higher stability. SQuAD 2.0 is an extension of SQuAD 1.1 by including unanswerable The FLOPs constraint is 60 % . There is a trade-off between sample dataset size and accuracy.

As showcased in Figure 1 (b), Learngene framework is designed in two pivotal stages.

Our study reveals the roles of critical parameters in the Transformer, such as the number of layers and the number of attention heads.