Related papers: DEED: Dynamic Early Exit on Decoder for Accelerati…

Out-of-distribution (OOD) detection is essential to prevent anomalous inputs from causing a model to fail during deployment. While improved OOD detection methods have emerged, they often rely on the final layer outputs and require a full…

We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results…

Ever-larger language models with ever-increasing capabilities are by now well-established text processing tools. Alas, information extraction tasks such as named entity recognition are still largely unaffected by this progress as they are…

The Encoder-Decoder architecture is a main stream deep learning model for biomedical image segmentation. The encoder fully compresses the input and generates encoded features, and the decoder then produces dense predictions using encoded…

Deep learning has been widely adopted to tackle various code-based tasks by building deep code models based on a large amount of code snippets. While these deep code models have achieved great success, even state-of-the-art models suffer…

In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We…

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…

Encoder-decoder foundation models have displayed state-of-the-art performance on a range of autoregressive sequence tasks. This paper proposes a simple and lightweight modification to such systems to control the behaviour according to a…

Deep learning (DL) models have emerged as a promising solution for the Internet of Things (IoT). However, due to their computational complexity, DL models consume significant amounts of energy, which can rapidly drain the battery and…

Intermediate-layer predictions in large language models (LLMs) are informative but hard to decode accurately, especially at early layers. Existing lens-style methods typically rely on direct linear readout, which is simple but often drifts…

Radiology Report Generation (RRG) aims to produce accurate and coherent diagnostics from medical images. Although large vision language models (LVLM) improve report fluency and accuracy, they exhibit hallucinations, generating plausible yet…

Recent work has shown that simple linear models can outperform several Transformer based approaches in long term time-series forecasting. Motivated by this, we propose a Multi-layer Perceptron (MLP) based encoder-decoder model, Time-series…

In this paper, we propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC). SAD optimizes the online inference efficiency for GEC by two…

We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression…

The ability to dynamically adjust the computational load of neural models during inference in a resource aware manner is crucial for on-device processing scenarios, characterised by limited and time-varying computational resources.…

Early Exiting (EE) is a promising technique for speeding up inference by adaptively allocating compute resources to data points based on their difficulty. The approach enables predictions to exit at earlier layers for simpler samples while…

The performance of deep learning based edge detector has far exceeded that of humans, but the huge computational cost and complex training strategy hinder its further development and application. In this paper, we eliminate these…

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Both performance and efficiency are crucial factors for sequence labeling tasks in many real-world scenarios. Although the pre-trained models (PTMs) have significantly improved the performance of various sequence labeling tasks, their…

The autoregressive nature of large language models (LLMs) fundamentally limits inference speed, as each forward pass generates only a single token and is often bottlenecked by memory bandwidth. Speculative decoding has emerged as a…