VINO: A Unified Visual Generator with Interleaved OmniModal Context Paper โข 2601.02358 โข Published 1 day ago โข 22
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows Paper โข 2512.16969 โข Published 20 days ago โข 111
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling Paper โข 2509.12201 โข Published Sep 15, 2025 โข 106
Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models Paper โข 2508.00819 โข Published Aug 1, 2025 โข 62
ฯ^3: Scalable Permutation-Equivariant Visual Geometry Learning Paper โข 2507.13347 โข Published Jul 17, 2025 โข 65
Aether: Geometric-Aware Unified World Modeling Paper โข 2503.18945 โข Published Mar 24, 2025 โข 28