Related papers: E$^2$CM: Early Exit via Class Means for Efficient …

In machine learning practice, early stopping has been widely used to regularize models and can save computational costs by halting the training process when the model's performance on a validation set stops improving. However, conventional…

Transformer-based pre-trained language models (PLMs) mostly suffer from excessive overhead despite their advanced capacity. For resource-constrained devices, there is an urgent need for a spatially and temporally efficient model which…

Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference. Multi-exit is a mainstream approach to address this issue by making a trade-off between…

The deployment of inference services at the network edge, called edge inference, offloads computation-intensive inference tasks from mobile devices to edge servers, thereby enhancing the former's capabilities and battery lives. In a…

In Large Language Model (LLM) inference, early-exit refers to stopping computation at an intermediate layer once the prediction is sufficiently confident, thereby reducing latency and cost. However, recent LLMs adopt improved pretraining…

Contour-based instance segmentation methods have developed rapidly recently but feature rough and hand-crafted front-end contour initialization, which restricts the model performance, and an empirical and fixed backend predicted-label…

Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Modeling (ESLM), a risk-aware algorithm that improves training…

Multi-Exit models (MEMs) use an early-exit strategy to improve the accuracy and efficiency of deep neural networks (DNNs) by allowing samples to exit the network before the last layer. However, the effectiveness of MEMs in the presence of…

Many DNN-enabled vision applications constantly operate under severe energy constraints such as unmanned aerial vehicles, Augmented Reality headsets, and smartphones. Designing DNNs that can meet a stringent energy budget is becoming…

Collaborative inference systems are one of the emerging solutions for deploying deep neural networks (DNNs) at the wireless network edge. Their main idea is to divide a DNN into two parts, where the first is shallow enough to be reliably…

Recent advances in large reasoning language models (LRLMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks. However, overthinking in long CoT not only slows down the efficiency of…

Early-Exit Large Language Models (EE-LLMs) enable high throughput inference by allowing tokens to exit early at intermediate layers. However, their throughput is limited by the computational and memory savings. Existing EE-LLM frameworks…

Multimodal deep neural networks enhance deep comprehension by integrating diverse data modalities. Data from different modalities are typically projected into a shared latent space for similarity computation, but this process is resource…

Large Reasoning Models (LRMs) often suffer from \emph{overthinking}, a phenomenon in which redundant reasoning steps are generated after a correct solution has already been reached. Existing early reasoning exit methods primarily rely on…

Extreme Learning Machines (ELM) provide a fast alternative to traditional gradient-based learning in neural networks, offering rapid training and robust generalization capabilities. Its theoretical basis shows its universal approximation…

The ensemble of deep neural networks has been shown, both theoretically and empirically, to improve generalization accuracy on the unseen test set. However, the high training cost hinders its efficiency since we need a sufficient number of…

Recent advances in autoregressive (AR) models have demonstrated their potential to rival diffusion models in image synthesis. However, for complex spatially-conditioned generation, current AR approaches rely on fine-tuning the pre-trained…

The emergence of Long Short-Term Memory (LSTM) solves the problems of vanishing gradient and exploding gradient in traditional Recurrent Neural Networks (RNN). LSTM, as a new type of RNN, has been widely used in various fields, such as text…

Well-trained deep neural networks (DNNs) treat all test samples equally during prediction. Adaptive DNN inference with early exiting leverages the observation that some test examples can be easier to predict than others. This paper presents…

The End-to-end (E2E) learning-based approach has great potential to reshape the existing communication systems by replacing the transceivers with deep neural networks. To this end, the E2E learning approach needs to assume the availability…