Related papers: CARL: Aggregated Search with Context-Aware Module …
We describe a modern deep learning system that automatically identifies informative contextual examples (\qu{contexts}) for first language vocabulary instruction for high school student. Our paper compares three modeling approaches: (i) an…
Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative…
Retrieval-augmented generation (RAG) systems rely on accurate document retrieval to ground large language models (LLMs) in external knowledge, yet retrieval quality often degrades in corpora where topics overlap and thematic variation is…
Large vision-language models (LVLMs) are typically trained using autoregressive language modeling objectives, which align visual representations with linguistic space. While effective for multimodal reasoning, this alignment can weaken…
Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL),…
In-Context Learning (ICL) enables Large Language Models (LLMs) to perform new tasks by conditioning on prompts with relevant information. Retrieval-Augmented Generation (RAG) enhances ICL by incorporating retrieved documents into the LLM's…
Cloze-style reading comprehension has been a popular task for measuring the progress of natural language understanding in recent years. In this paper, we design a novel multi-perspective framework, which can be seen as the joint training of…
Semi-supervised learning has become increasingly popular in medical image segmentation due to its ability to leverage large amounts of unlabeled data to extract additional information. However, most existing semi-supervised segmentation…
Learning to rank is a key component of many e-commerce search engines. In learning to rank, one is interested in optimising the global ordering of a list of items according to their utility for users.Popular approaches learn a scoring…
Context-aware recommender systems (CARSs) apply sensing and analysis of user context in order to provide personalized services. Adding context to a recommendation model is challenging, since the addition of context may increases both the…
Prior works on action representation learning mainly focus on designing various architectures to extract the global representations for short video clips. In contrast, many practical applications such as video alignment have strong demand…
Knowledge graph completion (KGC) aims to solve the incompleteness of knowledge graphs (KGs) by predicting missing links from known triples, numbers of knowledge graph embedding (KGE) models have been proposed to perform KGC by learning…
Heavy-Encoder-Light-Decoder (HELD) neural routing solvers have emerged as a promising paradigm due to their broad applicability across multiple vehicle routing problems (VRPs). However, they typically struggle with VRP variants with complex…
Constituting highly informative network embeddings is an important tool for network analysis. It encodes network topology, along with other useful side information, into low-dimensional node-based feature representations that can be…
Agents capable of accomplishing complex tasks through multiple interactions with the environment have emerged as a popular research direction. However, in such multi-step settings, the conventional group-level policy optimization algorithm…
Many users struggle with effective online search and critical evaluation, especially in high-stakes domains like health, while often overestimating their digital literacy. Thus, in this demo, we present an interactive search companion that…
Context-aware recommendation systems improve upon classical recommender systems by including, in the modelling, a user's behaviour. Research into context-aware recommendation systems has previously only considered the sequential ordering of…
Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences. We propose to view text classification as a label-word joint embedding…
Prognostic Health Management (PHM) systems monitor and predict equipment health. A key task is Remaining Useful Life (RUL) estimation, which predicts how long a component, such as a rolling element bearing, will operate before failure. Many…
Current large language models (LLMs), even those explicitly trained for reasoning, often struggle with ambiguous content moderation cases due to misleading "decision shortcuts" embedded in context. Inspired by cognitive psychology insights…