NVIDIA GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published Jan 8 • 234
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published Jan 8 • 234
Qwen Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition Paper • 2512.15603 • Published Dec 17, 2025 • 70
Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition Paper • 2512.15603 • Published Dec 17, 2025 • 70
DisneyResearch Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views Paper • 2601.03362 • Published Jan 6 • 3
Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views Paper • 2601.03362 • Published Jan 6 • 3
Qwen Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition Paper • 2512.15603 • Published Dec 17, 2025 • 70
Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition Paper • 2512.15603 • Published Dec 17, 2025 • 70
NVIDIA GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published Jan 8 • 234
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published Jan 8 • 234
DisneyResearch Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views Paper • 2601.03362 • Published Jan 6 • 3
Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views Paper • 2601.03362 • Published Jan 6 • 3
