Exploring MLLM-Diffusion Information Transfer with MetaCanvas Paper • 2512.11464 • Published Dec 12, 2025 • 12
WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World Paper • 2512.10958 • Published Dec 11, 2025
BabyVision Collection State-of-the-art MLLMs achieve PhD-level language reasoning but struggle with visual tasks that 3-year-olds solve effortlessly. • 2 items • Updated 5 days ago • 4
The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding Paper • 2512.19693 • Published 24 days ago • 63
Exploring MLLM-Diffusion Information Transfer with MetaCanvas Paper • 2512.11464 • Published Dec 12, 2025 • 12
Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark Paper • 2510.13759 • Published Oct 15, 2025 • 10
Simulating the Visual World with Artificial Intelligence: A Roadmap Paper • 2511.08585 • Published Nov 11, 2025 • 29
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image Paper • 2511.13648 • Published Nov 17, 2025 • 52
Simulating the Visual World with Artificial Intelligence: A Roadmap Paper • 2511.08585 • Published Nov 11, 2025 • 29
Simulating the Visual World with Artificial Intelligence: A Roadmap Paper • 2511.08585 • Published Nov 11, 2025 • 29 • 3
The Quest for Generalizable Motion Generation: Data, Model, and Evaluation Paper • 2510.26794 • Published Oct 30, 2025 • 26
The Quest for Generalizable Motion Generation: Data, Model, and Evaluation Paper • 2510.26794 • Published Oct 30, 2025 • 26
RealDPO: Real or Not Real, that is the Preference Paper • 2510.14955 • Published Oct 16, 2025 • 6 • 2
Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark Paper • 2510.13759 • Published Oct 15, 2025 • 10
VBench: Comprehensive Benchmark Suite for Video Generative Models Paper • 2311.17982 • Published Nov 29, 2023 • 9