21. O Octrees as an Explicit 3D Language paper: https://t.co/2elFVL3CK5 Octrees as an Explicit 3D Language paper: huggingface.co/papers/2610.02… Your browser does not support the video tag. 🔗 View on Twitter 💬 4 🔄 10 ❤️ 89  10/05 12:09 ♡
22. E EditHero A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling paper: https://t.co/... EditHero A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling paper: huggingface.co/papers/2610.02… Your browser does not support the video tag. 🔗 View on T 10/05 12:07 ♡
23. Adaptive Reward Routing Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forwa... Adaptive Reward Routing Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL paper: huggingface.co/papers/2609.37… 💬 9 🔄 7 ❤️ 56 10/03 01:54 ♡
24. E EgoTools Towards Tool-Centric Reasoning in Real-World Egocentric Videos paper: https://t.co/DYdf8d... EgoTools Towards Tool-Centric Reasoning in Real-World Egocentric Videos paper: huggingface.co/papers/2609.39… Your browser does not support the video tag. 🔗 View on Twitter 10/03 00:49 ♡
25. L LongLive-Plug Once-for-All Distillation for Video Generation paper: https://t.co/hi1n0h3Ud9 LongLive-Plug Once-for-All Distillation for Video Generation paper: huggingface.co/papers/2609.38… Your browser does not support the video tag. 🔗 View on Twitter 💬 10/01 06:59 ♡
26. O Omni-IO Skills Harnessing Your Agent Omni-Native paper: https://t.co/k9IQB40rPe Omni-IO Skills Harnessing Your Agent Omni-Native paper: huggingface.co/papers/2609.31… Your browser does not support the video tag. 🔗 View on Twitter 💬 4 🔄 10/01 06:56 ♡
27. L LEGO-Anything Coding Agents for 3D Scene Reconstruction paper: https://t.co/lWpBbRNuP8 LEGO-Anything Coding Agents for 3D Scene Reconstruction paper: huggingface.co/papers/2609.36… Your browser does not support the video tag. 🔗 View on Twitter 💬 15 &# 10/01 06:51 ♡
28. I I will be at the Hugging Face Open Together event at the Midway in SF on October 16th sign up here:... I will be at the Hugging Face Open Together event at the Midway in SF on October 16th sign up here: luma.com/OpenTogether Your browser does not support the video tag. 🔗 Vie 10/01 03:34 ♡
29. SpatialClaw Rethinking Action Interface for Agentic Spatial Reasoning paper: https://t.co/gR8yH41J... SpatialClaw Rethinking Action Interface for Agentic Spatial Reasoning paper: huggingface.co/papers/2606.13… 💬 20 🔄 14 ❤️ 95 👀 18272 📊 34 ⚡ Powered b 09/30 15:49 ♡
30. A Audio8 ASR Infinite streaming speech recognition model the native streaming architecture decodes 1... Audio8 ASR Infinite streaming speech recognition model the native streaming architecture decodes 12.5 times per second a rolling KV Cache keeps both memory and latency constant, ev 09/30 11:32 ♡
