Related papers: PreciseCache: Precise Feature Caching for Efficien…
Leveraging recent advancements in large language models, modern neural code completion models have demonstrated the capability to generate highly accurate code suggestions. However, their massive size poses challenges in terms of…
Masked autoregressive (MAR) models unify the strengths of masked and autoregressive generation by predicting tokens in a fixed order using bidirectional attention for image generation. While effective, MAR models suffer from significant…
Current video generation models perform well at single-shot synthesis but struggle with multi-shot videos, facing critical challenges in maintaining character and background consistency across shots and flexibly generating videos of…
Long-context video understanding and generation pose a significant computational challenge for Transformer-based video models due to the quadratic complexity of self-attention. While existing sparse attention methods employ coarse-grained…
Caching at the wireless edge can be used to keep up with the increasing demand for high-definition wireless video streaming. By prefetching popular content into memory at wireless access points or end-user devices, requests can be served…
Diffusion models produce realistic images and videos but require substantial computational resources, necessitating multi-accelerator parallelism for real-time deployment. However, parallel inference introduces significant communication…
Language models are increasingly adopting smaller architectures optimized for consumer devices. In this setting, inference efficiency is the primary constraint. Meanwhile, vocabulary sizes continue to grow rapidly, making the classification…
Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improving the inference…
While many hardware accelerators have recently been proposed to address the inefficiency problem of fully homomorphic encryption (FHE) schemes, none of them is able to deliver optimal performance when facing real-world FHE workloads…
Caching and reusing intermediate features across consecutive frames is a common technique to reduce redundant computation and transmission for edge-cloud video analytics in mobile edge computation. Existing methods manage the cache in a…
The evaluation of material networks is a relatively resource-intensive process in the rendering pipeline. Modern production scenes can contain hundreds or thousands of complex materials with massive networks, so there is a great demand for…
Modern computer scaling trends in pursuit of larger component counts and power efficiency have, unfortunately, lead to less reliable hardware and consequently soft errors escaping into application data ("silent data corruptions").…
Considering the current price gap between disk and flash memory drives, for applications dealing with large scale data, it will be economically more sensible to use flash memory drives to supplement disk drives rather than to replace them.…
Storage systems have a strong need for substantially improving their error correction capabilities, especially for long-term storage where the accumulating errors can exceed the decoding threshold of error-correcting codes (ECCs). In this…
This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings,…
Diffusion Transformers currently lead the field in high-quality video generation, but their slow iterative denoising process and prohibitive quadratic attention costs for long sequences create significant inference bottlenecks. While both…
Human animation aims to generate temporally coherent and visually consistent videos over long sequences, yet modeling long-range dependencies while preserving frame quality remains challenging. Inspired by the human ability to leverage past…
Diffusion and flow matching models have unlocked unprecedented capabilities for creative content creation, such as interactive image and streaming video generation. The growing demand for higher resolutions, frame rates, and context…
Autoregressive video diffusion models enable streaming generation, opening the door to long-form synthesis, video world models, and interactive neural game engines. However, their core attention layers become a major bottleneck at inference…
Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and diffusion models. It generates images by progressively…