✳flâneur — a map of the web's best reading
NVlabs/AutoGaze: AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x. ·
github.com · 936 words · saved by 1 readers
AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
Explore this link on the map →saved by
related reading
- Rewind.ai - Every AI Tool, Completely Freerewind.ai
- There's An AI For That® — The front page of AItheresanaiforthat.com
- Reducto: The Agentic Document Platform for AI Teamsreducto.ai
- Arcads - Create winning ads with AIarcads.ai
- Denis Shiryaev | AI & ML Projectsshir-man.com
- GitHub - x1xhlol/system-prompts-and-models-of-ai-tools: FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Tragithub.com
- Home | Genmogenmo.ai
- GitHub - Jiayi-Pan/TinyZero: Minimal reproduction of DeepSeek R1-Zero · GitHubgithub.com
- Swishy - AI Motion Designer & Animator | Create Stunning Animationsswishy.ai
- GitHub - Masao-Taketani/FOTS_OCR: TensorFlow Implementation of FOTS, Fast Oriented Text Spotting with a Unified Network. · GitHubgithub.com
- GitHub - ml5js/training-styletransfer: Style Transfer training and using the model in ml5js · GitHubgithub.com
- GitHub - google/hackable_diffusion · GitHubgithub.com