Related papers: Head Forcing: Long Autoregressive Video Generation…

We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time…

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

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…

As multi-object tracking (MOT) tasks continue to evolve toward more general and multi-modal scenarios, the rigid and task-specific architectures of existing MOT methods increasingly hinder their applicability across diverse tasks and limit…

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…

Existing video frame interpolation (VFI) methods often adopt a frame-centric approach, processing videos as independent short segments (e.g., triplets), which leads to temporal inconsistencies and motion artifacts. To overcome this, we…

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…

In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds,…

Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing…

Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field. To address these issues, we…

Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents significant challenges. Recent work, the masked autoregressive…

Video generation models have demonstrated remarkable performance, yet their broader adoption remains constrained by slow inference speeds and substantial computational costs, primarily due to the iterative nature of the denoising process.…

As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising. Previous methods speed up the models by caching and reusing model outputs at uniformly…

Autoregressive transformers have shown remarkable success in video generation. However, the transformers are prohibited from directly learning the long-term dependency in videos due to the quadratic complexity of self-attention, and…

Recent advancements in video generation models, like Stable Video Diffusion, show promising results, but primarily focus on short, single-scene videos. These models struggle with generating long videos that involve multiple scenes, coherent…

Training-free high-resolution (HR) image generation has garnered significant attention due to the high costs of training large diffusion models. Most existing methods begin by reconstructing the overall structure and then proceed to refine…

Existing long-term video prediction methods often rely on an autoregressive video prediction mechanism. However, this approach suffers from error propagation, particularly in distant future frames. To address this limitation, this paper…

Efficiently handling long contexts in transformer-based language models with low perplexity is an active area of research. Numerous recent approaches like Linformer, Longformer, Performer, and Structured state space models (SSMs)., have not…

Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cache reuse methods face a fundamental trade-off: prefix caching requires identical prefixes…

Long-trajectory video generation is a crucial yet challenging task for world modeling primarily due to the limited scalability of existing video diffusion models (VDMs). Autoregressive models, while offering infinite rollout, suffer from…