Related papers: Break a Lag: Triple Exponential Moving Average for…
The success of deep learning can be attributed to various factors such as increase in computational power, large datasets, deep convolutional neural networks, optimizers etc. Particularly, the choice of optimizer affects the generalization,…
The emergence of large foundation models has propelled significant advances in various domains. The Segment Anything Model (SAM), a leading model for image segmentation, exemplifies these advances, outperforming traditional methods.…
A variety of statistical and machine learning methods are used to model crash frequency on specific roadways with machine learning methods generally having a higher prediction accuracy. Recently, heterogeneous ensemble methods (HEM),…
Most current video MLLMs rely on uniform frame sampling and image-level encoders, resulting in inefficient data processing and limited motion awareness. To address these challenges, we introduce EMA, an Efficient Motion-Aware video MLLM…
We consider first order gradient methods for effectively optimizing a composite objective in the form of a sum of smooth and, potentially, non-smooth functions. We present accelerated and adaptive gradient methods, called FLAG and FLARE,…
Utilizing large pre-trained models for specific tasks has yielded impressive results. However, fully fine-tuning these increasingly large models is becoming prohibitively resource-intensive. This has led to a focus on more…
We propose a new model to assess the mastery level of a given skill efficiently. The model, called Bayesian Adaptive Mastery Assessment (BAMA), uses information on the accuracy and the response time of the answers given and infers the…
Modern machine learning systems operating in dynamic environments often face \textit{sequential covariate shift} (SCS), where input distributions evolve over time while the conditional distribution remains stable. We introduce FADE…
End-to-end motion planning is promising for simplifying complex autonomous driving pipelines. However, challenges such as scene understanding and effective prediction for decision-making continue to present substantial obstacles to its…
Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend…
Event cameras have the ability to record continuous and detailed trajectories of objects with high temporal resolution, thereby providing intuitive motion cues for optical flow estimation. Nevertheless, most existing learning-based…
Facial emotional recognition is one of the essential tools used by recognition psychology to diagnose patients. Face and facial emotional recognition are areas where machine learning is excelling. Facial Emotion Recognition in an…
Deep learning-based trajectory prediction models for autonomous driving often struggle with generalization to out-of-distribution (OOD) scenarios, sometimes performing worse than simple rule-based models. To address this limitation, we…
Multi-modal fusion is crucial for Internet of Things (IoT) perception, widely deployed in smart homes, intelligent transport, industrial automation, and healthcare. However, existing systems often face challenges: high model complexity…
The availability of precise and accurate simulation is a limiting factor for interpreting and forecasting data in many fields of science and engineering. Often, one or more distinct simulation software applications are developed, each with…
Transformer models have revolutionized natural language processing, achieving state-of-the-art performance and demonstrating remarkable scalability. However, their memory demands, particularly due to maintaining full context in memory, pose…
Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder…
Recently, autoregressive recommendation models (ARMs), such as Meta's HSTU model, have emerged as a major breakthrough over traditional Deep Learning Recommendation Models (DLRMs), exhibiting the highly sought-after scaling law behaviour.…
The minimum action method (MAM) is to calculate the most probable transition path in randomly perturbed stochastic dynamics, based on the idea of action minimization in the path space. The accuracy of the numerical path between different…
Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…