相关论文: Tiny is not small enough: High-quality, low-resour…

Diffusion-based models have gained wide adoption in the virtual human generation due to their outstanding expressiveness. However, their substantial computational requirements have constrained their deployment in real-time interactive…

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelmed by global context. Recent "Thinking-with-Images" methods…

Speech-driven 3D facial animation has been an attractive task in both academia and industry. Traditional methods mostly focus on learning a deterministic mapping from speech to animation. Recent approaches start to consider the…

There is a growing need for social robots and intelligent agents that can effectively interact with and support users. For the interactions to be seamless, the agents need to analyse social scenes and behavioural cues from their (robot's)…

The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature…

Large language models have led to significant progress across many NLP tasks, although their massive sizes often incur substantial computational costs. Distillation has become a common practice to compress these large and highly capable…

A number of studies have demonstrated the efficacy of deep learning convolutional neural network (CNN) models for ocular-based user recognition in mobile devices. However, these high-performing networks have enormous space and computational…

Much research effort is being applied to the task of compressing the knowledge of self-supervised models, which are powerful, yet large and memory consuming. In this work, we show that the original method of knowledge distillation (and its…

Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yielding a more useful general language model. Hence, we are…

This paper presents FaceXHuBERT, a text-less speech-driven 3D facial animation generation method that allows to capture personalized and subtle cues in speech (e.g. identity, emotion and hesitation). It is also very robust to background…

Developing deep learning models to analyze histology images has been computationally challenging, as the massive size of the images causes excessive strain on all parts of the computing pipeline. This paper proposes a novel deep…

Self-supervised speech pre-training enables deep neural network models to capture meaningful and disentangled factors from raw waveform signals. The learned universal speech representations can then be used across numerous downstream tasks.…

The Whisper model, an open-source automatic speech recognition system, is widely adopted for its strong performance across multilingual and zero-shot settings. However, it frequently suffers from hallucination errors, especially under noisy…

The development of computer vision solutions for gigapixel images in digital pathology is hampered by significant computational limitations due to the large size of whole slide images. In particular, digitizing biopsies at high resolutions…

Artificial Intelligence (AI) has increasingly influenced modern society, recently in particular through significant advancements in Large Language Models (LLMs). However, high computational and storage demands of LLMs still limit their…

All previous methods for audio-driven talking head generation assume the input audio to be clean with a neutral tone. As we show empirically, one can easily break these systems by simply adding certain background noise to the utterance or…

In order to be widely applicable, speech-driven 3D head avatars must articulate their lips in accordance with speech, while also conveying the appropriate emotions with dynamically changing facial expressions. The key problem is that…

We present a deep learning framework for real-time speech-driven 3D facial animation from just raw waveforms. Our deep neural network directly maps an input sequence of speech audio to a series of micro facial action unit activations and…

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model…