In contrast, transformers employ a "Scaled Dot-Product Attention" mechanism that is parallelizable. This unique attention mechanism allows for large-scale pretraining. Additionally, self-supervised pretraining paradigm such as masked language modeling onlarge unlabeled datasets enabled transformers to be trained without costly annotations. Transformer model, although originally designed for the NLP [3] domain, Transformers have witnessed adaptations in various domains such as computer vision [5, 6], remote sensing [7], time series [8], speech processing [9] and multimodal learning [10]. Consequently, modality specific surveys emerged, focusing on medical imaging [11-13] and biomedical language models [14] in the medical domain. This paper aims to provide comprehensive overview of Transformer models utilized across multiple modalities of data to address healthcare objectives. We discuss pre-training strategies to manage the lack of robust and annotated healthcare datasets. The rest of the paper is organized as follows: Section 2 discusses the strategy to search for relevant citations; Section 3 describes the architecture of the original transformer; Section 4 describes the two primary Transformer variants: the Bidirectional Encoder Representations from Transformers (BERT) and the Vision Transformer (ViT). Section 5 describes advancements in large language models (LLM), and section 6 through 12 provides a review of Transformers in healthcare.

Due to effective pattern mining and feature representation, neural forecasting models based on deep learning have achieved great progress. The premise of effective learning is to collect sufficient data. However, in time series forecasting, it is difficult to obtain enough data, which limits the performance of neural forecasting models. To alleviate the data scarcity limitation, we design Sequence Decomposition Adaptation Network (SeDAN) which is a novel transfer architecture to improve forecasting performance on the target domain by aligning transferable knowledge from cross-domain datasets. Rethinking the transferability of features in time series data, we propose Implicit Contrastive Decomposition to decompose the original features into components including seasonal and trend features, which are easier to transfer. Then we design the corresponding adaptation methods for decomposed features in different domains. Specifically, for seasonal features, we perform joint distribution adaptation and for trend features, we design an Optimal Local Adaptation. We conduct extensive experiments on five benchmark datasets for multivariate time series forecasting. The results demonstrate the effectiveness of our SeDAN. It can provide more efficient and stable knowledge transfer.

Classifier-Free Guidance (CFG) [37] has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrate that CFG can be used broadly as an inference-time technique in pure language modeling. We show that CFG (1) improves the performance of Pythia, GPT-2 and LLaMA-family models across an array of tasks: Q&A, reasoning, code generation, and machine translation, achieving SOTA on LAMBADA with LLaMA-7B over PaLM-540B; (2) brings improvements equivalent to a model with twice the parameter-count; (3) can stack alongside other inference-time methods like Chain-of-Thought and Self-Consistency, yielding further improvements in difficult tasks; (4) can be used to increase the faithfulness and coherence of assistants in challenging form-driven and content-driven prompts: in a human evaluation we show a 75% preference for GPT4All using CFG over baseline.

Visualization is a crucial step in exploratory data analysis. One possible approach is to train an autoencoder with low-dimensional latent space. Large network depth and width can help unfolding the data. However, such expressive networks can achieve low reconstruction error even when the latent representation is distorted. To avoid such misleading visualizations, we propose first a differential geometric perspective on the decoder, leading to insightful diagnostics for an embedding's distortion, and second a new regularizer mitigating such distortion. Our ``Geometric Autoencoder'' avoids stretching the embedding spuriously, so that the visualization captures the data structure more faithfully. It also flags areas where little distortion could not be achieved, thus guarding against misinterpretation.

Can knowing where you are assist in perceiving objects in your surroundings, especially under adverse weather and lighting conditions? In this work we investigate whether a prior map can be leveraged to aid in the detection of dynamic objects in a scene without the need for a 3D map or pixel-level map-query correspondences. We contribute an algorithm which refines an initial set of candidate object detections and produces a refined subset of highly accurate detections using a prior map. We begin by using visual place recognition (VPR) to retrieve a reference map image for a given query image, then use a binary classification neural network that compares the query and mapping image regions to validate the query detection. Once our classification network is trained, on approximately 1000 query-map image pairs, it is able to improve the performance of vehicle detection when combined with an existing off-the-shelf vehicle detector. We demonstrate our approach using standard datasets across two cities (Oxford and Zurich) under different settings of train-test separation of map-query traverse pairs. We further emphasize the performance gains of our approach against alternative design choices and show that VPR suffices for the task, eliminating the need for precise ground truth localization.

Most 6-DoF localization and SLAM systems use static landmarks but ignore dynamic objects because they cannot be usefully incorporated into a typical pipeline. Where dynamic objects have been incorporated, typical approaches have attempted relatively sophisticated identification and localization of these objects, limiting their robustness or general utility. In this research, we propose a middle ground, demonstrated in the context of autonomous vehicles, using dynamic vehicles to provide limited pose constraint information in a 6-DoF frame-by-frame PnP-RANSAC localization pipeline. We refine initial pose estimates with a motion model and propose a method for calculating the predicted quality of future pose estimates, triggered based on whether or not the autonomous vehicle's motion is constrained by the relative frame-to-frame location of dynamic vehicles in the environment. Our approach detects and identifies suitable dynamic vehicles to define these pose constraints to modify a pose filter, resulting in improved recall across a range of localization tolerances from $0.25m$ to $5m$, compared to a state-of-the-art baseline single image PnP method and its vanilla pose filtering. Our constraint detection system is active for approximately $35\%$ of the time on the Ford AV dataset and localization is particularly improved when the constraint detection is active.

Deep neural networks often suffer from poor generalization due to complex and non-convex loss landscapes. Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of training loss when adding a perturbation to the weight. However, indiscriminate perturbation of SAM on all parameters is suboptimal and results in excessive computation, double the overhead of common optimizers like Stochastic Gradient Descent (SGD). In this paper, we propose Sparse SAM (SSAM), an efficient and effective training scheme that achieves sparse perturbation by a binary mask. To obtain the sparse mask, we provide two solutions based on Fisher information and dynamic sparse training, respectively. We investigate the impact of different masks, including unstructured, structured, and $N$:$M$ structured patterns, as well as explicit and implicit forms of implementing sparse perturbation. We theoretically prove that SSAM can converge at the same rate as SAM, i.e., $O(\log T/\sqrt{T})$. Sparse SAM has the potential to accelerate training and smooth the loss landscape effectively. Extensive experimental results on CIFAR and ImageNet-1K confirm that our method is superior to SAM in terms of efficiency, and the performance is preserved or even improved with a perturbation of merely 50\% sparsity. Code is available at https://github.com/Mi-Peng/Systematic-Investigation-of-Sparse-Perturbed-Sharpness-Aware-Minimization-Optimizer.

Speech emotion recognition (SER) is vital for obtaining emotional intelligence and understanding the contextual meaning of speech. Variations of consonant-vowel (CV) phonemic boundaries can enrich acoustic context with linguistic cues, which impacts SER. In practice, speech emotions are treated as single labels over an acoustic segment for a given time duration. However, phone boundaries within speech are not discrete events, therefore the perceived emotion state should also be distributed over potentially continuous time-windows. This research explores the implication of acoustic context and phone boundaries on local markers for SER using an attention-based approach. The benefits of using a distributed approach to speech emotion understanding are supported by the results of cross-corpora analysis experiments. Experiments where phones and words are mapped to the attention vectors along with the fundamental frequency to observe the overlapping distributions and thereby the relationship between acoustic context and emotion. This work aims to bridge psycholinguistic theory research with computational modelling for SER.

We consider a micromanipulation problem in eye surgery, specifically retinal vein cannulation (RVC). RVC involves inserting a microneedle into a retinal vein for the purpose of targeted drug delivery. The procedure requires accurately guiding a needle to a target vein and inserting it while avoiding damage to the surrounding tissues. RVC can be considered similar to the reach or push task studied in robotics manipulation, but with additional constraints related to precision and safety while interacting with soft tissues. Prior works have mainly focused developing robotic hardware and sensors to enhance the surgeons' accuracy, leaving the automation of RVC largely unexplored. In this paper, we present the first autonomous strategy for RVC while relying on a minimal setup: a robotic arm, a needle, and monocular images. Our system exclusively relies on monocular vision to achieve precise navigation, gentle placement on the target vein, and safe insertion without causing tissue damage. Throughout the procedure, we employ machine learning for perception and to identify key surgical events such as needle-vein contact and vein punctures. Detecting these events guides our task and motion planning framework, which generates safe trajectories using model predictive control to complete the procedure. We validate our system through 24 successful autonomous trials on 4 cadaveric pig eyes. We show that our system can navigate to target veins within 22 micrometers of XY accuracy and under 35 seconds, and consistently puncture the target vein without causing tissue damage. Preliminary comparison to a human demonstrates the superior accuracy and reliability of our system.

Machine learning risks reinforcing biases present in data, and, as we argue in this work, in what is absent from data. In healthcare, biases have marked medical history, leading to unequal care affecting marginalised groups. Patterns in missing data often reflect these group discrepancies, but the algorithmic fairness implications of group-specific missingness are not well understood. Despite its potential impact, imputation is often an overlooked preprocessing step, with attention placed on the reduction of reconstruction error and overall performance, ignoring how imputation can affect groups differently. Our work studies how imputation choices affect reconstruction errors across groups and algorithmic fairness properties of downstream predictions.