GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published 1 day ago • 104
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times Paper • 2512.16093 • Published 23 days ago • 93
Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition Paper • 2512.15603 • Published 24 days ago • 60
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows Paper • 2512.16969 • Published 23 days ago • 111
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance Paper • 2512.08765 • Published Dec 9, 2025 • 128
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer Paper • 2511.22699 • Published Nov 27, 2025 • 225
Smoothie Qwen3 Collection For more details, please visit https://github.com/dnotitia/smoothie-qwen • 9 items • Updated Jul 24, 2025 • 7
Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs Paper • 2507.05686 • Published Jul 8, 2025 • 1
HuBERT Collection A collection of checkpoints from the HuBERT release, a speech encoder that learns powerful representations from unlabelled audio data. • 6 items • Updated Jan 16, 2024 • 8