MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning Paper • 2507.16812 • Published 7 days ago • 46
PUSA V1.0: Surpassing Wan-I2V with $500 Training Cost by Vectorized Timestep Adaptation Paper • 2507.16116 • Published 7 days ago • 9
NeuralOS: Towards Simulating Operating Systems via Neural Generative Models Paper • 2507.08800 • Published 18 days ago • 74
The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs Paper • 2507.11097 • Published 14 days ago • 56
NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining Paper • 2507.14119 • Published 11 days ago • 49
SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction Paper • 2507.15852 • Published 8 days ago • 36
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning Paper • 2507.01006 • Published 28 days ago • 200
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers Paper • 2506.23918 • Published 29 days ago • 82
WebSailor: Navigating Super-human Reasoning for Web Agent Paper • 2507.02592 • Published 26 days ago • 100
LongAnimation: Long Animation Generation with Dynamic Global-Local Memory Paper • 2507.01945 • Published 27 days ago • 74
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model Paper • 2504.08685 • Published Apr 11 • 129