Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices. Pruning and quantization address this, but rely on manual, expert choices and on algorithms that are hard to apply across architectures.
arXiv:2608. 05499v1 Announce Type: cross Abstract: Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices.
arXiv:2606. 07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications.
arXiv:2608. 15693v1 Announce Type: new Abstract: Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation.
arXiv:2603. 12222v2 Announce Type: replace-cross Abstract: Vision Transformers require significant computational resources and memory bandwidth, severely limiting their deployment on resource-constraint hardware.
arXiv:2505. 03303v3 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.
arXiv:2505. 03303v4 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints.
arXiv:2606. 27866v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models scale model ability with sparsely activated experts, making this architecture a standard recipe for modern large models.
arXiv:2606. 26488v1 Announce Type: new Abstract: Recursive reasoning models can solve complex structured tasks with only a few million parameters by repeatedly updating a latent state.
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.
Deep neural networks have witnessed remarkable advancements in recent years and have become integral to various applications. However, alongside these developments, training and deployment of neural network models on embedding and edge devices face significant challenges due to limited memory and computational resources.
arXiv:2606. 26587v1 Announce Type: cross Abstract: Low-bit floating-point formats and semi-structured sparsity are increasingly supported by modern accelerators, yet combining them for LLM activation compression remains challenging: activations contain input-dependent outliers that dominate block scales in FP4 quantization, and directly applying N:M sparsity masks discards moderate values, coupling sparsification loss with quantization error.
arXiv:2606. 04620v1 Announce Type: cross Abstract: LLMs have become the state-of-the-art algorithms for solving NLP tasks.