Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments Paper • 2605.30280 • Published May 28 • 146
Seedance 2.0: Advancing Video Generation for World Complexity Paper • 2604.14148 • Published Apr 15 • 169
MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier Paper • 2603.03756 • Published Mar 4 • 90
ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding Paper • 2508.21496 • Published Aug 29, 2025 • 55
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps Paper • 2501.09732 • Published Jan 16, 2025 • 72
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites Paper • 2404.16821 • Published Apr 25, 2024 • 60
