Running 33 Audiosr Versatile Audio Super Resolution π 33 Versatile audio super resolution (any -> 48kHz) with AudioSR
Visual Representation Alignment for Multimodal Large Language Models Paper β’ 2509.07979 β’ Published Sep 9 β’ 83
Running on Zero MCP Featured 2.55k Wan2.2 14B Fast π₯ 2.55k generate a video from an image with a text prompt
LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion Paper β’ 2507.02813 β’ Published Jul 3 β’ 60
Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention Paper β’ 2507.17745 β’ Published Jul 23 β’ 35
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning Paper β’ 2507.14295 β’ Published Jul 18 β’ 13
The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner Paper β’ 2507.13332 β’ Published Jul 17 β’ 48
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation Paper β’ 2507.10524 β’ Published Jul 14 β’ 70