Related papers: USDC: Unified Static and Dynamic Compression for V…
There has been a growing trend in compressing and transmitting videos from terminals for machine vision tasks. Nevertheless, most video coding optimization method focus on minimizing distortion according to human perceptual metrics,…
Robotic manipulation has seen rapid progress with vision-language-action (VLA) policies. However, visuo-tactile perception is critical for contact-rich manipulation, as tasks such as insertion are difficult to complete robustly using vision…
Deep neural networks are powerful, yet their high complexity greatly limits their potential to be deployed on billions of resource-constrained edge devices. Pruning is a crucial network compression technique, yet most existing methods focus…
Large language models have steadily increased in size to achieve improved performance; however, this growth has also led to greater inference time and computational demands. Consequently, there is rising interest in model size reduction…
While the performance of recent learned intra and sequential video compression models exceed that of respective traditional codecs, the performance of learned B-frame compression models generally lag behind traditional B-frame coding. The…
Training large-scale distributed machine learning models imposes considerable demands on network infrastructure, often resulting in sudden traffic spikes that lead to congestion, increased latency, and reduced throughput, which would…
Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…
Massive amounts of data have led to the training of large-scale machine learning models on a single worker inefficient. Distributed machine learning methods such as Parallel-SGD have received significant interest as a solution to tackle…
The input tokens to Vision Transformers carry little semantic meaning as they are defined as regular equal-sized patches of the input image, regardless of its content. However, processing uniform background areas of an image should not…
The promising improvement in compression efficiency of Versatile Video Coding (VVC) compared to High Efficiency Video Coding (HEVC) comes at the cost of a non-negligible encoder side complexity. The largely increased complexity overhead is…
Transformer plays a vital role in the realms of natural language processing (NLP) and computer vision (CV), specially for constructing large language models (LLM) and large vision models (LVM). Model compression methods reduce the memory…
Large-scale Transformer models are known for their exceptional performance in a range of tasks, but training them can be difficult due to the requirement for communication-intensive model parallelism. One way to improve training speed is to…
Recently, vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in the realm of computer vision (CV). With the general-purpose Transformer architecture replacing…
Extensive work has demonstrated the effectiveness of Vision Transformers. The plain Vision Transformer tends to obtain multi-scale features by selecting fixed layers, or the last layer of features aiming to achieve higher performance in…
We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing…
An emerging paradigm in vision-and-language navigation (VLN) is the use of history-aware multi-modal transformer models. Given a language instruction, these models process observation and navigation history to predict the most appropriate…
Neural Radiance Field (NeRF)-based volumetric video has revolutionized visual media by delivering photorealistic Free-Viewpoint Video (FVV) experiences that provide audiences with unprecedented immersion and interactivity. However, the…
Recent advancements in deep learning-based image compression are notable. However, prevalent schemes that employ a serial context-adaptive entropy model to enhance rate-distortion (R-D) performance are markedly slow. Furthermore, the…
Video generative models can be regarded as world simulators due to their ability to capture dynamic, continuous changes inherent in real-world environments. These models integrate high-dimensional information across visual, temporal,…
Diffusion Transformers (DiTs) can generate short photorealistic videos, yet directly training and sampling longer videos with full attention across the video remains computationally challenging. Alternative methods break long videos down…