arXiv:2601.03290v1 Announce Type: new Abstract: The deployment of transformer-based models on resource-constrained edge devices represents a critical challenge in enabling real-time artificial intelligence applications. This comprehensive survey examines lightweight transformer architectures specifically designed for edge deployment, analyzing recent advances in model compression, quantization, pruning, and knowledge distillation techniques. We systematically review prominent lightweight variants including MobileBERT, TinyBERT, DistilBERT, EfficientFormer, EdgeFormer, and MobileViT, providing detailed performance benchmarks on standard datasets such as GLUE, SQuAD, ImageNet-1K, and COCO. Our analysis […]

Ver mais

As context lengths move into tens and hundreds of thousands of tokens, the key value cache in transformer decoders becomes a primary deployment bottleneck. The cache stores keys and values for every layer and head with shape (2, L, H, T, D). For a vanilla transformer such as Llama1-65B, the cache reaches about 335 GB at 128k tokens in bfloat16, which directly limits batch size and increases time to first token. https://arxiv.org/pdf/2601.07891 Architectural compression leaves the sequence axis […]

Ver mais

arXiv:2601.01594v3 Announce Type: replace Abstract: We study variance reduction for score estimation and diffusion-based sampling in settings where the clean (target) score is available or can be approximated. Starting from the Target Score Identity (TSI), which expresses the noisy marginal score as a conditional expectation of the target score under the forward diffusion, we develop: (i) a plug-and-play nonparametric self-normalized importance sampling estimator compatible with standard reverse-time solvers, (ii) a variance-minimizing emph{state- and time-dependent} blending rule between Tweedie-type […]

Ver mais

arXiv:2504.03097v2 Announce Type: replace Abstract: In this paper, we study the problem of multivariate shuffled linear regression, where the correspondence between predictors and responses in a linear model is obfuscated by a latent permutation. Specifically, we investigate the model $Y=tfrac{1}{sqrt{1+sigma^2}}(Pi_* X Q_* + sigma Z)$, where $X$ is an $n*d$ standard Gaussian design matrix, $Z$ is an $n*m$ Gaussian noise matrix, $Pi_*$ is an unknown $n*n$ permutation matrix, and $Q_*$ is an unknown $d*m$ on the Grassmanian manifold […]

Ver mais

According to statistics, Python is the second most popular programming language in the world. There are more than 600,000 Python jobs in the world, which makes up to 20% of all programming jobs. Even though Python is more than thirty years old, it still doesn’t lose its popularity. In this article, you will learn about the pros and cons of Python that make this programming language so special. If you’re a beginner programmer, this article might convince you […]

Ver mais

In-context learning (ICL) enables Large Language Models (LLMs) to adapt to new tasks with only a small set of examples at inference time, thereby avoiding task-specific fine-tuning. However, in-context examples may contain privacy-sensitive information that should not be revealed through model outputs. Existing differential privacy (DP) approaches to ICL are either computationally expensive or rely on heuristics with limited effectiveness, including context oversampling, synthetic data generation, or unnecessary thresholding. We reformulate private ICL through the lens of a […]

Ver mais

arXiv:2602.05174v1 Announce Type: new Abstract: Riemannian flow matching (RFM) extends flow-based generative modeling to data supported on manifolds by learning a time-dependent tangent vector field whose flow-ODE transports a simple base distribution to the data law. We develop a nonasymptotic Total Variation (TV) convergence analysis for RFM samplers that use a learned vector field together with Euler discretization on manifolds. Our key technical ingredient is a differential inequality governing the evolution of TV between two manifold ODE flows, […]

Ver mais