We consider a Bayesian approach to offline model-based inverse reinforce...
Large language models (LLMs) have recently demonstrated remarkable
capab...
Vision-Language Pre-training (VLP) methods based on object detection enj...
The research field of Information Retrieval (IR) has evolved significant...
Vision Transformer (ViT) based Vision-Language Pre-training (VLP) models...
Document understanding refers to automatically extract, analyze and
comp...
Recently, Multi-Scenario Learning (MSL) is widely used in recommendation...
In this paper, a class of smoothing modulus-based iterative method was
p...
To promote the development of Vision-Language Pre-training (VLP) and
mul...
The goal of unbiased learning to rank (ULTR) is to leverage implicit use...
We propose to Transform Scene Graphs (TSG) into more descriptive caption...
Large language models (LLMs) have demonstrated impressive zero-shot abil...
Aspect-based sentiment analysis (ABSA) aims at automatically inferring t...
In this paper, we present ChatPLUG, a Chinese open-domain dialogue syste...
Mainstream solutions to Sequential Recommendation (SR) represent items w...
Offline inverse reinforcement learning (Offline IRL) aims to recover the...
Recent years have witnessed a big convergence of language, vision, and
m...
We design a novel global-local Transformer named Ada-ClustFormer
(ACF) t...
Aligning objects with words plays a critical role in Image-Language BERT...
Inverse reinforcement learning (IRL) aims to recover the reward function...
Learning dynamic user preference has become an increasingly important
co...
Multi-modal document pre-trained models have proven to be very effective...
In recent years, many practitioners in quantitative finance have attempt...
Multi-scenario learning (MSL) enables a service provider to cater for us...
Large-scale pretrained foundation models have been an emerging paradigm ...
Session-based recommendation aims to predict items that an anonymous use...
Knowledge Graphs (KGs) have been utilized as useful side information to
...
In academic research, recommender systems are often evaluated on benchma...
The Visual Question Answering (VQA) task utilizes both visual image and
...
Existing approaches to vision-language pre-training (VLP) heavily rely o...
Vision-language pre-training (VLP) on large-scale image-text pairs has
a...
Large pre-trained language models achieve state-of-the-art results when
...
The large-scale recommender system mainly consists of two stages: matchi...
Vision-language pre-training (VLP) on large-scale image-text pairs has
r...
In academic research, recommender models are often evaluated offline on
...
Popularity is often included in experimental evaluation to provide a
ref...
In a large recommender system, the products (or items) could be in many
...
Most of ranking models are trained only with displayed items (most are h...
Recently, large-scale datasets have vastly facilitated the development i...
Self-supervised pre-training has emerged as a powerful technique for nat...
In this paper, we define and study a new task called Context-Aware Seman...
Current neural Natural Language Generation (NLG) models cannot handle
em...
Commonsense and background knowledge is required for a QA model to answe...
Identifying the named entities mentioned in text would enrich many seman...
Recently, with the prevalence of large-scale image dataset, the co-occur...
User reviews contain rich semantics towards the preference of users to
f...
Writing review for a purchased item is a unique channel to express a use...
Targeted sentiment analysis (TSA), also known as aspect based sentiment
...
The users often have many product-related questions before they make a
p...
In recent years, with the prevalence of social media and smart devices,
...