Related papers: X-Cache: Cross-Chunk Block Caching for Few-Step Au…

Diffusion-based image generation models excel at producing high-quality synthetic content, but suffer from slow and computationally expensive inference. Prior work has attempted to mitigate this by caching and reusing features within…

Long-form video question answering (VQA) overwhelms current vision-language models (VLMs) because attention and key-value (KV) caches grow with runtime, forcing either expensive inference or near-sighted sliding windows. We introduce…

Although Diffusion Transformer (DiT) has emerged as a predominant architecture for image and video generation, its iterative denoising process results in slow inference, which hinders broader applicability and development. Caching-based…

Physical world knowledge resides mainly in videos. Equipping Vision-Language-Action (VLA) models with such knowledge is fundamental for safe and generalizable planning. Predictive world modeling enables VLA to internalize physical dynamics…

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…

We propose PostCam, a framework for novel-view video generation that enables post-capture editing of camera trajectories in dynamic scenes. We find that existing video recapture methods suffer from suboptimal camera motion injection…

Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure. While prior methods accelerate sampling by…

We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruction) in a single framework, addressing the critical limitations of prior unified world…

Quantization and cache mechanisms are typically applied individually for efficient Diffusion Transformers (DiTs), each demonstrating notable potential for acceleration. However, the promoting effect of combining the two mechanisms on…

With the advancement of interactive video generation, diffusion models have increasingly demonstrated their potential as world models. However, existing approaches still struggle to simultaneously achieve memory-enabled long-term temporal…

Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses…

Video generation is pivotal to digital media creation, and recent advances in autoregressive video generation have markedly enhanced the efficiency of real-time video synthesis. However, existing approaches generally rely on heuristic KV…

Long-context video modeling is essential for enabling generative models to function as world simulators, as they must maintain temporal coherence over extended time spans. However, most existing models are trained on short clips, limiting…

Enterprises are increasingly deploying large camera networks for video analytics. Many target applications entail a common problem template: searching for and tracking an object or activity of interest (e.g. a speeding vehicle, a break-in)…

Embodied AI agents increasingly require parallel execution of multiple tasks, such as manipulation, conversation, and memory construction, from shared observations under distinct time constraints. Recent Mixture-of-Transformers (MoT)…

The task of video generation requires synthesizing visually realistic and temporally coherent video frames. Existing methods primarily use asynchronous auto-regressive models or synchronous diffusion models to address this challenge.…

Diffusion Transformers (DiT) have emerged as powerful generative models for various tasks, including image, video, and speech synthesis. However, their inference process remains computationally expensive due to the repeated evaluation of…

Despite its great potential, virtual try-on technology is hindered from real-world application by two major challenges: the inability of current methods to support multi-reference outfit compositions (including garments and accessories),…

Generating long-duration videos has always been a significant challenge due to the inherent complexity of spatio-temporal domain and the substantial GPU memory demands required to calculate huge size tensors. While diffusion based…

Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks. A key challenge in accelerating VLMs is storing and accessing the large Key-Value (KV) cache that encodes long visual contexts, such as…