Skip to content
Papers.

In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion research paper by Meta, 2026

Meta · Sep 26, 2026 · Inference and efficiency · 34 upvotes · unverified 9 days ago

Read on arXiv

What it shows

Few-step autoregressive video diffusion generates a long video by splitting the video into temporal chunks and generating chunk-by-chunk, each through a short sequence of denoising stages.

By Yikai Wang, Xiao Han, Mengmeng Xu and 9 more · arXiv 2609.32540 · PDF

UnverifiedHugging Face's summary; not yet checked by hand.

More from Meta

All 37
PaperCitations
Sharpening Tax in Post-TrainingAn emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of a base model, improving single-shot accuracy at the cost of...Training and scaling · Oct 2026 · Unverified4 days ago-
Context Language ModelsWe introduce Context Language Models (CLMs), language models that natively manage their own context.Agents and evaluation · Sep 2026 · Unverified6 days ago-
WearableQA: A Benchmark for Health Reasoning over Real-World Wearable DataWearableQA is a benchmark of multiple-choice questions derived from real longitudinal wearable data that evaluates large language model reasoning across data and health dimensions.Agents and evaluation · Sep 2026 · Unverified4 weeks ago0
Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and RecipesControlled experiments on when text, image understanding and image generation help or compete when trained together.Multimodal and robotics · Aug 20262 months ago2
HumanCLAW: Can Vision-Language Models Act Through a Body?HumanCLAW decouples high-level vision-language decisions from low-level motor execution to evaluate embodied action intelligence, revealing that current vision-language models lack embodied self-awareness.Multimodal and robotics · Jul 2026 · Unverified2 months ago2
TUA-Bench: A Benchmark for General-Purpose Terminal-Use AgentsTUA-Bench presents a comprehensive benchmark for evaluating general-purpose terminal-use agents across diverse digital activities and specialized workflows, revealing significant performance gaps among current frontier agents.Agents and evaluation · Jun 2026 · Unverified3 months ago4
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved ReasoningProcess-driven image generation decomposes synthesis into iterative steps involving textual planning, visual drafting, textual reflection, and visual refinement, with step-wise supervision ensuring consistency and interpretability.Reasoning · Apr 2026 · Unverified6 months ago5
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised LearningV-JEPA 2.1 is a self-supervised model that learns dense visual representations for images and videos through a combination of dense predictive loss, deep self-supervision, multi-modal tokenizers, and effective scaling.Multimodal and robotics · Mar 2026 · Unverified6 months ago106

Other inference and efficiency papers

Topic
PaperCitations
Efficient Memory Management for Large Language Model Serving with PagedAttentionvLLM manages the KV cache like pages of virtual memory, serving models with 2 to 4 times the throughput.UC Berkeley · Sep 20233 years ago8,815
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessFlashAttention computes exact attention with far fewer GPU memory reads and writes, making long sequences faster.Stanford University · May 20224 years ago5,460
Group Sequence Policy OptimizationGroup Sequence Policy Optimization (GSPO) is a reinforcement learning algorithm that improves training efficiency and performance of large language models by using sequence-level importance ratios and operations.Alibaba (Qwen) · Jul 2025 · Unverified1 year ago722
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionNSA, a trainable sparse attention mechanism, enhances long-context modeling efficiency without sacrificing performance, achieving improvements in speed and accuracy over full attention models.DeepSeek · Feb 2025 · Unverified1 year ago531
SmolVLM: Redefining small and efficient multimodal modelsSmolVLM, a series of compact multimodal models, achieves high performance with minimal GPU memory usage, making efficient deployment on mobile and edge devices possible.Hugging Face · Apr 2025 · Unverified1 year ago305
Inference-Time Scaling for Generalist Reward ModelingSelf-Principled Critique Tuning enhances pointwise generative reward modeling for large language models, improving scalability and quality compared to existing methods.DeepSeek · Apr 2025 · Unverified1 year ago251
About this paper
Authors
Yikai Wang, Xiao Han, Mengmeng Xu and 9 more
arXiv
2609.32540 · PDF
Citations
Not counted yet · Semantic Scholar
Upvotes
34 · Hugging Face
Lab
Meta · on Companies · on Acquisitions · on Quarterly · on Paydays · on TechConf

Changes

What changed
New paperFound by the weekly scan, unverifiedOct 5, 2026today

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.