SGF+: Decoupling Gradient Flows for Autoregressive Video Generation Paper • 2610.10429 • Published 2 days ago • 51
Qianfan-VL: Domain-Enhanced Universal Vision-Language Models Paper • 2509.18189 • Published Sep 19, 2025 • 4
DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation Paper • 2610.03543 • Published 7 days ago • 79
Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR Paper • 2603.20020 • Published May 26
DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation Paper • 2610.03543 • Published 7 days ago • 79
Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence Paper • 2607.16401 • Published Jul 17 • 45
AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model Paper • 2604.19747 • Published Apr 21 • 41
ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing Paper • 2508.10881 • Published Aug 14, 2025 • 54