Related papers: Future Forcing: Future-aware Training-free KV Cach…

A fundamental challenge in Visual Autoregressive models is the substantial memory overhead required during inference to store previously generated representations. Despite various attempts to mitigate this issue through compression…

Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences. Existing reinforcement learning (RL) frameworks are not naturally suited to these architectures,…

Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning through both text and image inputs. Although VLMs enrich the capabilities of language…

Streaming video large language models (LLMs) are increasingly used for real-time multimodal tasks such as video captioning, question answering, conversational agents, and augmented reality. However, these models face fundamental memory and…

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…

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…

Video-to-video synthesis poses significant challenges in maintaining character consistency, smooth temporal transitions, and preserving visual quality during fast motion. While recent fully cross-frame self-attention mechanisms have…

Generative reasoning with large language models (LLMs) often involves long decoding sequences, leading to substantial memory and latency overheads from accumulating key-value (KV) caches. While existing KV compression methods primarily…

Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to…

We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel…

With the advance of diffusion models, today's video generation has achieved impressive quality. But generating temporal consistent long videos is still challenging. A majority of video diffusion models (VDMs) generate long videos in an…

Autoregressive (AR) image models have recently demonstrated remarkable generative capability, but their sequential nature results in significant inference latency. Existing training-free acceleration methods typically verify tokens…

As Large Language Models (LLMs) scale in size and context length, the memory requirements of the key value (KV) cache have emerged as a major bottleneck during autoregressive decoding. The KV cache grows with sequence length and embedding…

Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation. Despite the numerous efforts in this area, the optimization for the decoding phase is generally ignored. However, we believe such optimization is crucial,…

The memory and computational demands of Key-Value (KV) cache present significant challenges for deploying long-context language models. Previous approaches attempt to mitigate this issue by selectively dropping tokens, which irreversibly…

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…

In the rapidly advancing field of image generation, Visual Auto-Regressive (VAR) modeling has garnered considerable attention for its innovative next-scale prediction approach. This paradigm offers substantial improvements in efficiency,…

Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In this work, we revisit…

With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context generation. To compress the KV cache, recent methods…

Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To address these challenges, we make two contributions. First,…