paper-with-me

홈 › Papers

Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion

2026-01-29 · Hanmo Chen, Chenghao Xu, Xu Yang, Xuan Chen, Cheng Deng arxiv

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 Cache policies, which ignore differences in token importance in long-term video generation. This leads to the loss of critical spatiotemporal information and the accumulation of redundant, invalid cache, thereby degrading video generation quality and efficiency. To address this limitation, we first observe that token contributions to video generation are highly time-heterogeneous and accordingly propose a novel Past- and Future-Informed KV Cache Policy (PaFu-KV). Specifically, PaFu-KV introduces a lightweight Salience Estimation Head distilled from a bidirectional teacher to estimate salience scores, allowing the KV cache to retain informative tokens while discarding less relevant ones. This policy yields a better quality-efficiency trade-off by shrinking KV cache capacity and reducing memory footprint at inference time. Extensive experiments on benchmarks demonstrate that our method preserves high-fidelity video generation quality while enables accelerated inference, thereby enabling more efficient long-horizon video generation. Our code will be released upon paper acceptance.

📄 PDF Abstract BibTeX arXiv:2601.21896

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

An Imitation Learning Approach for Cache Replacement

2020-06-29 · ICML 2020 1 · Evan Zheran Liu, Milad Hashemi, Kevin Swersky, Parthasarathy Ranganathan 외

Program execution speed critically depends on increasing cache hits, as cache hits are orders of magnitude faster than misses. To increase cache hits, we focus on the problem of cache replacement: choosing which cache li…

Imitation Learning

Learning to Evict from Key-Value Cache

2026-02-10 · Luca Moschella, Laura Manduchi, Ozan Sener arxiv

The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache. Existing eviction or compression methods reduce cost…

Reinforcement LearningPassage Retrieval

DEAP Cache: Deep Eviction Admission and Prefetching for Cache

2020-09-19 · Ayush Mangal, Jitesh Jain, Keerat Kaur Guliani, Omkar Bhalerao

Recent approaches for learning policies to improve caching, target just one out of the prefetching, admission and eviction processes. In contrast, we propose an end to end pipeline to learn all three policies using machi…

BIG-bench Machine LearningDensity Estimation

Learning Long-Context Diffusion Policies via Past-Token Prediction

2025-05-14 · Marcel Torne, Andy Tang, Yuejiang Liu, Chelsea Finn

Reasoning over long sequences of observations and actions is essential for many robotic tasks. Yet, learning effective long-context policies from demonstrations remains challenging. As context length increases, training …

Imitation Learning

Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation

2026-05-28 · Jiayi Luo, Qiyan Liu, Tengyang Wang, JunHao Liu 외 arxiv

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache i…

Video Generation