Video models are zero-shot learners and reasoners

N/A

# link_13vn6wz50ev.pdf ## Metadata - PDFFormatVersion=1.7 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - Author=Thaddäus Wiedemer; Yuxuan Li; Paul Vicol; Shixiang Shane Gu; Nick Matarese; Kevin Swersky; Been Kim; Priyank Jaini; Robert Geirhos - Creator=arXiv GenPDF (tex2pdf:) - Custom.DOI=https://doi.org/10.48550/arXiv.2509.20328 - Custom.License=http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.28 (TeX Live 2025) kpathsea version 6.4.1 - Custom

saved by

• Dhruv Sheth
• Pranav Jadhav

related reading

• [2404.02905] Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictionarxiv.org
• Video Generation Models Explosion 2024yenchenlin.me
• [2602.10098] VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelarxiv.org
• Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website
• 2403.09611.pdfarxiv.org
• [2506.09985] V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningarxiv.org
• the-illusion-of-thinking.pdfml-site.cdn-apple.com
• [2206.11795] Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videosarxiv.org
• 2501.05874arxiv.org
• 45d74e190008c7bff2845ffc8e3facd3-Paper-Conference.pdfproceedings.iclr.cc
• [2508.16201] SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruningarxiv.org
• Self-Adapting Language Modelsarxiv.org