Related papers: PackCache: A Training-Free Acceleration Method for…

Key-value (KV) caching has emerged as a crucial optimization technique for accelerating inference in large language models (LLMs). By allowing the attention operation to scale linearly rather than quadratically with the total sequence…

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…

The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling…

When transformer-based language models are deployed for text generation, most of the inference time is spent in the decoding stage, where output tokens are generated sequentially. Reducing the hardware cost of each decoding step is…

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…

Autoregressive and diffusion models drive the recent breakthroughs on text-to-image generation. Despite their huge success of generating high-realistic images, a common shortcoming of these models is their high inference latency -…

Autoregressive video diffusion models generate streaming video by producing frames sequentially, conditioning each chunk on previously generated content. These models are structurally anchored to the first frame: its key-value…

Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compression strategy, relying on stage-specific…

Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we…

Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity, Diffusion Transformers (DiT) remain computationally…

As large language models (LLMs) continue to advance, the demand for higher quality and faster processing of long contexts across various applications is growing. KV cache is widely adopted as it stores previously generated key and value…

Recent advances have substantially improved real-time interactive video generation in the autoregressive regime. However, most existing few-step autoregressive video generation methods, often distilled from a corresponding many-step…

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…

Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache…

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of…

Modern large language models (LLMs) extend context lengths to millions of tokens, enabling coherent, personalized responses grounded in long conversational history. However, the Key-Value (KV) cache grows linearly with the extended dialogue…

Effective aggregation of temporal information of consecutive frames is the core of achieving video super-resolution. Many scholars have utilized structures such as sliding windows and recurrent to gather spatio-temporal information of…

The expanding long-context capabilities of large language models are constrained by a significant memory bottleneck: the key-value (KV) cache required for autoregressive generation. This bottleneck is substantial; for instance, a…

KV cache in autoregressive LLMs eliminates redundant recomputation but has emerged as the dominant memory and bandwidth bottleneck during inference, notably with long contexts and test-time scaling. KV quantization is a key lever for…

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…