惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Google DeepMind News
Google DeepMind News
I
InfoQ
Engineering at Meta
Engineering at Meta
D
DataBreaches.Net
L
LangChain Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Recent Announcements
Recent Announcements
GbyAI
GbyAI
爱范儿
爱范儿
Microsoft Security Blog
Microsoft Security Blog
腾
腾讯CDC
美
美团技术团队
罗
罗磊的独立博客
Microsoft Azure Blog
Microsoft Azure Blog
WordPress大学
WordPress大学
T
The Blog of Author Tim Ferriss
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
雷峰网
雷峰网
M
MIT News - Artificial intelligence
D
Docker
MongoDB | Blog
MongoDB | Blog
F
Fortinet All Blogs
博
博客园 - 叶小钗

cs.LG updates on arXiv.org

Memory-Guided Trust-Region Bayesian Optimization (MG-TuRBO) for High Dimensions EngageTriBoost: Predictive Modeling of User Engagement in Digital Mental Health Intervention Using Explainable Machine Learning Reservoir observer enhanced with residual calibration and attention mechanism Efficient RL Training for LLMs with Experience Replay Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning Adversarial Sensor Errors for Safe and Robust Wind Turbine Fleet Control IKKA: Inversion Classification via Critical Anomalies for Robust Visual Servoing Adaptive Simulation Experiment for LLM Policy Optimization EvoLen: Evolution-Guided Tokenization for DNA Language Model Smartwatch-Based Sitting Time Estimation in Real-World Office Settings Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis Loom: A Scalable Analytical Neural Computer Architecture Spectral Geometry of LoRA Adapters Encodes Training Objective and Predicts Harmful Compliance Finite-Sample Analysis of Nonlinear Independent Component Analysis:Sample Complexity and Identifiability Bounds How does Chain of Thought decompose complex tasks? Uncertainty-Aware Transformers: Conformal Prediction for Language Models Adaptive Candidate Point Thompson Sampling for High-Dimensional Bayesian Optimization Using Synthetic Data for Machine Learning-based Childhood Vaccination Prediction in Narok, Kenya Delve into the Applicability of Advanced Optimizers for Multi-Task Learning Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication Predictive Entropy Links Calibration and Paraphrase Sensitivity in Medical Vision-Language Models Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning Modality-Aware Zero-Shot Pruning and Sparse Attention for Efficient Multimodal Edge Inference The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge Feature-Label Modal Alignment for Robust Partial Multi-Label Learning Integrated electro-optic attention nonlinearities for transformers Toward World Models for Epidemiology Tracing the Chain: Deep Learning for Stepping-Stone Intrusion Detection Batch Distillation Data for Developing Machine Learning Anomaly Detection Methods
Quant VideoGen: Auto-Regressive Long Video Generation via...
Haocheng Xi, · 2026-05-05 · via cs.LG updates on arXiv.org

View PDF HTML (experimental)

Abstract:Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregressive video generation models, the KV cache grows with generation history and quickly dominates GPU memory, often exceeding 30 GB, preventing deployment on widely available hardware. More critically, constrained KV cache budgets restrict the effective working memory, directly degrading long horizon consistency in identity, layout, and motion. To address this challenge, we present Quant VideoGen (QVG), a training free KV cache quantization framework for autoregressive video diffusion models. QVG leverages video spatiotemporal redundancy through Semantic Aware Smoothing, producing low magnitude, quantization friendly residuals. It further introduces Progressive Residual Quantization, a coarse to fine multi stage scheme that reduces quantization error while enabling a smooth quality memory trade off. Across LongCat Video, HY WorldPlay, and Self Forcing benchmarks, QVG establishes a new Pareto frontier between quality and memory efficiency, reducing KV cache memory by up to 7.0 times with less than 4% end to end latency overhead while consistently outperforming existing baselines in generation quality. Code is available at: this https URL
Comments: Accepted by ICML 2026. 11 pages, 7 figures
Subjects: Machine Learning (cs.LG)
Cite as: arXiv:2602.02958 [cs.LG]
  (or arXiv:2602.02958v4 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2602.02958

arXiv-issued DOI via DataCite

Submission history

From: Haocheng Xi [view email]
[v1] Tue, 3 Feb 2026 00:54:32 UTC (15,339 KB)
[v2] Tue, 17 Feb 2026 23:49:23 UTC (15,339 KB)
[v3] Thu, 26 Feb 2026 23:08:15 UTC (15,339 KB)
[v4] Fri, 1 May 2026 19:28:18 UTC (15,339 KB)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。