Related papers: ENCODE: Breaking the Trade-Off Between Performance…
Performance of distributed optimization and learning systems is bottlenecked by "straggler" nodes and slow communication links, which significantly delay computation. We propose a distributed optimization framework where the dataset is…
Sequential recommendation plays an increasingly important role in many e-commerce services such as display advertisement and online shopping. With the rapid development of these services in the last two decades, users have accumulated a…
The widespread deployment of smartphones and location-enabled, networked in-vehicle devices renders it increasingly feasible to collect streaming trajectory data of moving objects. The continuous clustering of such data can enable a variety…
Predicting contextualised engagement in videos is a long-standing problem that has been popularly attempted by exploiting the number of views or the associated likes using different computational methods. The recent decade has seen a boom…
State-of-the-art sequential recommendation models heavily rely on transformer's attention mechanism. However, the quadratic computational and memory complexities of self attention have limited its scalability for modeling users' long range…
Feature interaction is a core ingredient in ranking models for large-scale recommender systems, yet making it both expressive and efficiently scalable remains challenging. Exhaustive pairwise interaction is powerful but incurs quadratic…
Recent methods in sequential recommendation focus on learning an overall embedding vector from a user's behavior sequence for the next-item recommendation. However, from empirical analysis, we discovered that a user's behavior sequence…
Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…
As e-commerce platforms expand their product catalogs, accurately recommending long-tail items becomes increasingly important for enhancing both user experience and platform revenue. A key challenge is the long-tail problem, where extreme…
Effective attention modules have played a crucial role in the success of Transformer-based large language models (LLMs), but the quadratic time and memory complexities of these attention modules also pose a challenge when processing long…
Pervasive mobile AI applications primarily employ one of the two learning paradigms: cloud-based learning (with powerful large models) or on-device learning (with lightweight small models). Despite their own advantages, neither paradigm can…
While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this…
Getting a robust time-series clustering with best choice of distance measure and appropriate representation is always a challenge. We propose a novel mechanism to identify the clusters combining learned compact representation of…
User response prediction is essential in industrial recommendation systems, such as online display advertising. Among all the features in recommendation models, user behaviors are among the most critical. Many works have revealed that a…
We present a new method for segmenting, and a new user interface for indexing and visualizing, the semantic content of extended instructional videos. Given a series of key frames from the video, we generate a condensed view of the data by…
Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on large-scale datasets. To…
End-to-end autonomous driving has made impressive progress in recent years. Existing methods usually adopt the decoupled encoder-decoder paradigm, where the encoder extracts hidden features from raw sensor data, and the decoder outputs the…
Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e.g., can be up to 2048X in large-scale ensemble tasks. However, we found that the majority of computations in ensemble…
The exponential growth of multivariate time series data from sensor networks in domains like industrial monitoring and smart cities requires efficient and accurate forecasting models. Current deep learning methods often fail to adequately…
Today's densely instrumented world offers tremendous opportunities for continuous acquisition and analysis of multimodal sensor data providing temporal characterization of an individual's behaviors. Is it possible to efficiently couple such…