Related papers: AntBatchInfer: Elastic Batch Inference in the Kube…
Modern Augmented reality applications require performing multiple tasks on each input frame simultaneously. Multi-task learning (MTL) represents an effective approach where multiple tasks share an encoder to extract representative features…
Clustering is an essential problem in machine learning and data mining. One vital factor that impacts clustering performance is how to learn or design the data representation (or features). Fortunately, recent advances in deep learning can…
The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV)…
Recently published methods enable training of bitwise neural networks which allow reduced representation of down to a single bit per weight. We present a method that exploits ensemble decisions based on multiple stochastically sampled…
The size and compute characteristics of modern large language models have led to an increased interest in developing specialized kernels tailored for particular training and inference workloads. Existing kernels primarily optimize for…
Industrial transfer learning increases the adaptability of deep learning algorithms towards heterogenous and dynamic industrial use cases without high manual efforts. The appropriate selection of what to transfer can vastly improve a…
Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However, traditional batching frameworks are ill-suited for EE…
Causal inference is a vital aspect of multiple scientific disciplines and is routinely applied to high-impact applications such as medicine. However, evaluating the performance of causal inference methods in real-world environments is…
1D-CNNs are used for time series classification in various domains with a high degree of accuracy. Most implementations collect the incoming data samples in a buffer before performing inference on it. On edge devices, which are typically…
Machine learning models are often implemented in cohort with humans in the pipeline, with the model having an option to defer to a domain expert in cases where it has low confidence in its inference. Our goal is to design mechanisms for…
DNN inference can be accelerated by distributing the workload among a cluster of collaborative edge nodes. Heterogeneity among edge devices and accuracy-performance trade-offs of DNN models present a complex exploration space while catering…
Large language model (LLM) inference often suffers from high latency, particularly in resource-constrained environments such as on-device or edge deployments. To address this challenge, we present StorInfer, a novel storage-assisted LLM…
For many practical, high-risk applications, it is essential to quantify uncertainty in a model's predictions to avoid costly mistakes. While predictive uncertainty is widely studied for neural networks, the topic seems to be under-explored…
Recent advances in large language models (LLMs) have shown remarkable performance across diverse tasks. However, these models are typically deployed with fixed weights, which limits their ability to adapt dynamically to the variability…
Modern digital applications extensively integrate Artificial Intelligence models into their core systems, offering significant advantages for automated decision-making. However, these AI-based systems encounter reliability and safety…
Deep neural network models have demonstrated their effectiveness in classifying multi-label data from various domains. Typically, they employ a training mode that combines mini-batches with optimizers, where each sample is randomly selected…
This paper proposes TIP-Search, a time-predictable inference scheduling framework for real-time market prediction under uncertain workloads. Motivated by the strict latency demands in high-frequency financial systems, TIP-Search dynamically…
The analysis of decision making under uncertainty is closely related to the analysis of probabilistic inference. Indeed, much of the research into efficient methods for probabilistic inference in expert systems has been motivated by the…
Amortized Bayesian inference trains neural networks to solve stochastic inference problems using model simulations, thereby making it possible to rapidly perform Bayesian inference for any newly observed data. However, current…
An artificial intelligence (AI) model can be viewed as a function that maps inputs to outputs in high-dimensional spaces. Once designed and well trained, the AI model is applied for inference. However, even optimized AI models can produce…