Related papers: Switchable Decision: Dynamic Neural Generation Net…

Generative models have proven to be an outstanding tool for representing high-dimensional probability distributions and generating realistic-looking images. An essential characteristic of generative models is their ability to produce…

Do all instances need inference through the big models for a correct prediction? Perhaps not; some instances are easy and can be answered correctly by even small capacity models. This provides opportunities for improving the computational…

The recent ground-breaking advances in deep learning networks ( DNNs ) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-limited embedded devices. Offloading the…

Attribution methods assess the contribution of inputs to the model prediction. One way to do so is erasure: a subset of inputs is considered irrelevant if it can be removed without affecting the prediction. Though conceptually simple,…

In a multi-stage recommendation system, reranking plays a crucial role in modeling intra-list correlations among items. A key challenge lies in exploring optimal sequences within the combinatorial space of permutations. Recent research…

Machine learning (ML) inference is a real-time workload that must comply with strict Service Level Objectives (SLOs), including latency and accuracy targets. Unfortunately, ensuring that SLOs are not violated in inference-serving systems is…

Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked lists. However, their practical deployment still faces two…

Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We…

Spiking neural networks are biologically plausible counterparts of the artificial neural networks, artificial neural networks are usually trained with stochastic gradient descent and spiking neural networks are trained with spike timing…

Deep reinforcement learning (DRL) techniques have become increasingly used in various fields for decision-making processes. However, a challenge that often arises is the trade-off between both the computational efficiency of the…

Large reasoning models that use long chain-of-thought excel at problem-solving yet waste compute on redundant checks. Curbing this overthinking is hard: training-time length penalties can cripple ability, while inference-time early-exit…

Implementing Deep Neural Networks (DNNs) on resource-constrained edge devices is a challenging task that requires tailored hardware accelerator architectures and a clear understanding of their performance characteristics when executing the…

This position paper proposes a fundamental shift in designing code generation models: treating reasoning depth as a controllable resource. Rather than being an incidental byproduct of prompting, we argue that the trade-off between rapid,…

Spiking Neural Networks (SNNs) are highly energy-efficient due to event-driven, sparse computation, but their training is challenged by spike non-differentiability and trade-offs among performance, efficiency, and biological plausibility.…

Datasets with missing values are very common on industry applications, and they can have a negative impact on machine learning models. Recent studies introduced solutions to the problem of imputing missing values based on deep generative…

Differentiable Logic Gate Networks (DLGNs) are a very fast and energy-efficient alternative to conventional feed-forward networks. With learnable combinations of logical gates, DLGNs enable fast inference by hardware-friendly execution.…

In the era of exceptionally data-hungry models, careful selection of the training data is essential to mitigate the extensive costs of deep learning. Data pruning offers a solution by removing redundant or uninformative samples from the…

Spiking neural networks are nature's versatile solution to fault-tolerant and energy efficient signal processing. To translate these benefits into hardware, a growing number of neuromorphic spiking neural network processors attempt to…

The topic of learning to solve optimization problems has received interest from both the operations research and machine learning communities. In this work, we combine techniques from both fields to address the problem of learning to…

In performative stochastic optimization, decisions can influence the distribution of random parameters, rendering the data-generating process itself decision-dependent. In practice, decision-makers rarely have access to the true…