Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Amazon launches Kiro, its own Claude-powered challenger to Windsurf and Codex

Meta built its AI reputation on openness — that may be changing

DeepMind’s AlphaEvolve AI: History In The Making!

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Industry AI
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Hugging Face

Paper page – Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective

By Advanced AI EditorJuly 14, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Lumos-1 is an autoregressive video generator that uses a modified LLM architecture with MM-RoPE and AR-DF to address spatiotemporal correlation and frame-wise loss imbalance, achieving competitive performance with fewer resources.

Autoregressive large language models (LLMs) have unified a vast range of
language tasks, inspiring preliminary efforts in autoregressive video
generation. Existing autoregressive video generators either diverge from
standard LLM architectures, depend on bulky external text encoders, or incur
prohibitive latency due to next-token decoding. In this paper, we introduce
Lumos-1, an autoregressive video generator that retains the LLM architecture
with minimal architectural modifications. To inject spatiotemporal correlations
in LLMs, we identify the efficacy of incorporating 3D RoPE and diagnose its
imbalanced frequency spectrum ranges. Therefore, we propose MM-RoPE, a RoPE
scheme that preserves the original textual RoPE while providing comprehensive
frequency spectra and scaled 3D positions for modeling multimodal
spatiotemporal data. Moreover, Lumos-1 resorts to a token dependency strategy
that obeys intra-frame bidirectionality and inter-frame temporal causality.
Based on this dependency strategy, we identify the issue of frame-wise loss
imbalance caused by spatial information redundancy and solve it by proposing
Autoregressive Discrete Diffusion Forcing (AR-DF). AR-DF introduces temporal
tube masking during training with a compatible inference-time masking policy to
avoid quality degradation. By using memory-efficient training techniques, we
pre-train Lumos-1 on only 48 GPUs, achieving performance comparable to EMU3 on
GenEval, COSMOS-Video2World on VBench-I2V, and OpenSoraPlan on VBench-T2V. Code
and models are available at https://github.com/alibaba-damo-academy/Lumos.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleHow Rapid7 automates vulnerability risk scores with ML pipelines using Amazon SageMaker AI
Next Article Autonomy, Governance, and the New Risk Equation
Advanced AI Editor
  • Website

Related Posts

Paper page – Test-Time Scaling with Reflective Generative Model

July 14, 2025

One Token to Fool LLM-as-a-Judge

July 14, 2025

Paper page – BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity

July 14, 2025

Comments are closed.

Latest Posts

Murujuga Rock Art in Australia Receives UNESCO World Heritage Status

‘Earth Room’ Caretaker Dies at 70

Racquel Chevremont on Showing Black Excellence on And Just Like That…

Homeland Security Targets Chicago’s National Museum of Puerto Rican Arts & Culture

Latest Posts

Amazon launches Kiro, its own Claude-powered challenger to Windsurf and Codex

July 14, 2025

Meta built its AI reputation on openness — that may be changing

July 14, 2025

DeepMind’s AlphaEvolve AI: History In The Making!

July 14, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Amazon launches Kiro, its own Claude-powered challenger to Windsurf and Codex
  • Meta built its AI reputation on openness — that may be changing
  • DeepMind’s AlphaEvolve AI: History In The Making!
  • Paper page – Test-Time Scaling with Reflective Generative Model
  • Build secure RAG applications with AWS serverless data lakes

Recent Comments

  1. Создать бесплатную учетную запись on NERFIES: The Selfies of The Future! 🤳
  2. Best SEO Backlinks on Tyler Cowen: Economic Growth & the Fight Against Conformity & Mediocrity | Lex Fridman Podcast #174
  3. binance on Veo 3 demo | Sailor and the sea
  4. Index Home on Nvidia, OpenAI, Oracle back UAE-leg of global Stargate AI mega-project
  5. código de indicac~ao binance on [2505.13511] Can AI Freelancers Compete? Benchmarking Earnings, Reliability, and Task Success at Scale

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.