Related papers: Progressive Supernet Training for Efficient Visual…

Scaling visual generation models is essential for real-world content creation, yet requires substantial training and computational expenses. Alternatively, test-time scaling has garnered growing attention due to resource efficiency and…

Deep Neural Networks have been used in a wide variety of applications with significant success. However, their highly complex nature owing to comprising millions of parameters has lead to problems during deployment in pipelines with low…

Conventional wisdom suggests that autoregressive models are used to process discrete data. When applied to continuous modalities such as visual data, Visual AutoRegressive modeling (VAR) typically resorts to quantization-based approaches to…

Large-scale autoregressive models have demonstrated remarkable capabilities in image generation. However, their sequential raster-scan decoding relies on strictly next-token prediction, making inference prohibitively expensive. Existing…

Decoder-only autoregressive image generation typically relies on fixed-length tokenization schemes whose token counts grow quadratically with resolution, substantially increasing the computational and memory demands of attention. We present…

Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality content generation with substantially fewer decoding steps. However, existing VAR models suffer from significant attention complexity and…

In contemporary neuroscience, a key area of interest is dynamic effective connectivity, which is crucial for understanding the dynamic interactions and causal relationships between different brain regions. Dynamic effective connectivity can…

Self-supervised learning methods for computer vision have demonstrated the effectiveness of pre-training feature representations, resulting in well-generalizing Deep Neural Networks, even if the annotated data are limited. However,…

The holy grail in deep neural network research is porting the memory- and computation-intensive network models on embedded platforms with a minimal compromise in model accuracy. To this end, we propose a novel approach, termed as…

Recent studies on Visual Autoregressive (VAR) models have highlighted that high-frequency components, or later steps, in the generation process contribute disproportionately to inference latency. However, the underlying computational…

Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communication constrained. To overcome this limitation, new gradient…

Deep autoregressive sequence-to-sequence models have demonstrated impressive performance across a wide variety of tasks in recent years. While common architecture classes such as recurrent, convolutional, and self-attention networks make…

Autoregressive sequence models based on deep neural networks, such as RNNs, Wavenet and the Transformer attain state-of-the-art results on many tasks. However, they are difficult to parallelize and are thus slow at processing long…

The rapid development of large-scale deep learning models questions the affordability of hardware platforms, which necessitates the pruning to reduce their computational and memory footprints. Sparse neural networks as the product, have…

Variational auto-encoder (VAE) is a powerful unsupervised learning framework for image generation. One drawback of VAE is that it generates blurry images due to its Gaussianity assumption and thus L2 loss. To allow the generation of high…

Contrastive learning has proven to be highly efficient and adaptable in shaping representation spaces across diverse modalities by pulling similar samples together and pushing dissimilar ones apart. However, two key limitations persist: (1)…

Recent developments in large language models have sparked interest in efficient pretraining methods. Stagewise training approaches to improve efficiency, like gradual stacking and layer dropping (Reddi et al, 2023; Zhang & He, 2020), have…

Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devices in federated learning, such as mobile phones and IoT…

Autoregressive vision-language models (VLMs) deliver strong multimodal capability, but their token-by-token decoding imposes a fundamental inference bottleneck. Diffusion VLMs offer a more parallel decoding paradigm, yet directly converting…

Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion ability. However, the extremely intensive requirements on memory…