Related papers: FastSTAR: Spatiotemporal Token Pruning for Efficie…
Learning descriptive spatio-temporal object models from data is paramount for the task of semi-supervised video object segmentation. Most existing approaches mainly rely on models that estimate the segmentation mask based on a reference…
Audio classification models, particularly the Audio Spectrogram Transformer (AST), play a crucial role in efficient audio analysis. However, optimizing their efficiency without compromising accuracy remains a challenge. In this paper, we…
Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in…
Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and…
Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…
Diffusion Language Models (DLMs) enable parallel decoding via iterative denoising, where remasking strategies play a critical role in balancing inference speed and output quality. Existing methods predominantly rely on static confidence…
Vision-language models (VLMs) have recently expanded from static image understanding to video reasoning, but their scalability is fundamentally limited by the quadratic cost of processing dense frame sequences. Long videos often exceed the…
Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a few seconds of video even on high-performance GPUs. This…
Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods…
Recent advancements in visual autoregressive models (VAR) have demonstrated their effectiveness in image generation, highlighting their potential for real-world image super-resolution (Real-ISR). However, adapting VAR for ISR presents…
Video large language models have demonstrated strong video understanding capabilities but suffer from high inference costs due to the massive number of tokens in long videos. Inspired by event-based vision, we propose an event-guided,…
Video generation has made significant strides with the development of diffusion models; however, achieving high temporal consistency remains a challenging task. Recently, FreeInit identified a training-inference gap and introduced a method…
Text-to-3D with diffusion models has achieved remarkable progress in recent years. However, existing methods either rely on score distillation-based optimization which suffer from slow inference, low diversity and Janus problems, or are…
Vision Transformer models have shown impressive effectiveness in the surgical video understanding tasks through long-range dependency modeling. However, current methods suffer from prohibitive computational costs due to processing massive…
Modern one-stage video instance segmentation networks suffer from two limitations. First, convolutional features are neither aligned with anchor boxes nor with ground-truth bounding boxes, reducing the mask sensitivity to spatial location.…
Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…
State-of-the-art super-resolution (SR) algorithms require significant computational resources to achieve real-time throughput (e.g., 60Mpixels/s for HD video). This paper introduces FAST (Free Adaptive Super-resolution via Transfer), a…
Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…
Diffusion models have made significant advances in generating high-quality images, but their application to video generation has remained challenging due to the complexity of temporal motion. Zero-shot video editing offers a solution by…
While 3D Multi-modal Large Language Models (MLLMs) demonstrate remarkable scene understanding capabilities, their practical deployment faces critical challenges due to computational inefficiency. The key bottleneck stems from processing…