Related papers: CAMTA: Causal Attention Model for Multi-touch Attr…
Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies. To advance TTA under…
Predicting users' preferences based on their sequential behaviors in history is challenging and crucial for modern recommender systems. Most existing sequential recommendation algorithms focus on transitional structure among the sequential…
Attribution methods for Vision Transformers (ViTs) aim to identify image regions that influence model predictions, but producing faithful and well-localized attributions remains challenging. Existing attribution methods face several…
To offer accurate and diverse recommendation services, recent methods use auxiliary information to foster the learning process of user and item representations. Many SOTA methods fuse different sources of information (user, item, knowledge…
As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and…
Click-through rate (CTR) prediction tasks play a pivotal role in real-world applications, particularly in recommendation systems and online advertising. A significant research branch in this domain focuses on user behavior modeling. Current…
Advertising click-through rate (CTR) prediction aims to forecast the probability that a user will click on an advertisement in a given context, thus providing enterprises with decision support for product ranking and ad placement. However,…
While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…
The rapid growth of 5G video streaming is intensifying energy consumption across access, core, and data-center networks, underscoring the critical need for energy and carbon-efficient solutions. While reducing streaming bitrates improves…
In Recommender systems, data representation techniques play a great role as they have the power to entangle, hide and reveal explanatory factors embedded within datasets. Hence, they influence the quality of recommendations. Specifically,…
Reliance on spurious correlations (shortcuts) has been shown to underlie many of the successes of language models. Previous work focused on identifying the input elements that impact prediction. We investigate how shortcuts are actually…
Deploying service robots in our daily life, whether in restaurants, warehouses or hospitals, calls for the need to reason on the interactions happening in dense and dynamic scenes. In this paper, we present and benchmark three new…
We consider a network of agents. Associated with each agent are her covariate and outcome. Agents influence each other's outcomes according to a certain connection/influence structure. A subset of the agents participate on a platform, and…
There is a growing interest in the transition from 4-step random access to 2-step random access in machine-type communication (MTC), since 2-step random access is well-suited to short message delivery in various Internet of Things (IoT)…
User behaviour targeting is essential in online advertising. Compared with sponsored search keyword targeting and contextual advertising page content targeting, user behaviour targeting builds users' interest profiles via tracking their…
Most existing One-Class Collaborative Filtering (OC-CF) algorithms estimate a user's preference as a latent vector by encoding their historical interactions. However, users often show diverse interests, which significantly increases the…
Modeling task-driven attention in driving is a fundamental challenge for both autonomous vehicles and cognitive science. Existing methods primarily predict where drivers look by generating spatial heatmaps, but fail to capture the cognitive…
Agentic systems increasingly rely on language models to monitor their own behavior. For example, coding agents may self critique generated code for pull request approval or assess the safety of tool-use actions. We show that this design…
The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model, which is a contrasting feature against Convolutional…
Attention level estimation systems have a high potential in many use cases, such as human-robot interaction, driver modeling and smart home systems, since being able to measure a person's attention level opens the possibility to natural…