We propose a novel framework to automatically learn to aggregate and
tra...
Conversational recommender systems (CRS) aim to provide the recommendati...
Although pre-trained language models (PLMs) have recently advanced the
r...
Neural radiance fields (NeRF) have shown great success in novel view
syn...
Conversational recommender systems (CRSs) aim to provide recommendation
...
Chain-of-thought prompting (CoT) and tool augmentation have been validat...
We introduce bidirectional edge diffraction response function (BEDRF), a...
Although large language models (LLMs) have achieved excellent performanc...
Inspired by the superior language abilities of large language models (LL...
In this paper, we study how to improve the zero-shot reasoning ability o...
Recently, continuous diffusion models (CDM) have been introduced into
no...
Neural radiance fields (NeRF) show great success in novel view synthesis...
Non-autoregressive (NAR) text generation has attracted much attention in...
Although pre-trained language models (PLMs) have shown impressive perfor...
Dense retrieval aims to map queries and passages into low-dimensional ve...
Multi-hop Question Answering over Knowledge Graph (KGQA) aims to find th...
Previous studies show the necessity of global and local adjustment for i...
Step-and-project is a popular way to simulate non-penetrated deformable
...
Emotional voice conversion (EVC) aims to convert the emotional state of ...
Sampling proper negatives from a large document pool is vital to effecti...
Emotional speech synthesis aims to synthesize human voices with various
...
Conversational recommender systems (CRS) aim to proactively elicit user
...
This paper aims to advance the mathematical intelligence of machines by
...
Undoubtedly, high-fidelity 3D hair plays an indispensable role in digita...
Commonsense reasoning in natural language is a desired ability of artifi...
We present a learning algorithm that uses bone-driven motion networks to...
Recently, contrastive learning has been shown to be effective in improvi...
Recent studies have shown the importance of modeling long-range interact...
We present a novel framework to efficiently acquire near-planar anisotro...
In this paper, we present NeuralReshaper, a novel method for semantic
re...
For video frame interpolation (VFI), existing deep-learning-based approa...
We present a novel framework to automatically learn to transform the
dif...
Recently, deep neural networks such as RNN, CNN and Transformer have bee...
In developing virtual acoustic environments, it is important to understa...
Emotional voice conversion (EVC) seeks to convert the emotional state of...
Conversational recommender systems (CRS) aim to recommend suitable items...
Long-range temporal alignment is critical yet challenging for video
rest...
Expressive voice conversion performs identity conversion for emotional
s...
Recent works have shown that powerful pre-trained language models (PLM) ...
In this paper, we present GCN-Denoiser, a novel feature-preserving mesh
...
A proactive dialogue system has the ability to proactively lead the
conv...
Traditional voice conversion(VC) has been focused on speaker identity
co...
Due to the flexibility in modelling data heterogeneity, heterogeneous
in...
In this paper, we first provide a review of the state-of-the-art emotion...
Single image super-resolution (SISR) deals with a fundamental problem of...
Emotional voice conversion (EVC) aims to change the emotional state of a...
We consider the single image super-resolution (SISR) problem, where a
hi...
We present a novel framework to learn to convert the perpixel photometri...
Sentence ordering aims to arrange the sentences of a given text in the
c...
Action recognition has been heavily employed in many applications such a...