Augmented Self (speech2speech) gpt-omni/mini-omni2 Any-to-Any • Updated Oct 24, 2024 • 114 • 285 sesame/csm-1b Text-to-Speech • 2B • Updated Dec 1, 2025 • 303k • 2.4k HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation Paper • 2505.04512 • Published May 7, 2025 • 36
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation Paper • 2505.04512 • Published May 7, 2025 • 36
Scaling test time compute 1B > 405B! Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper • 2502.05171 • Published Feb 7, 2025 • 158
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper • 2502.05171 • Published Feb 7, 2025 • 158
Augmented Self (speech2speech) gpt-omni/mini-omni2 Any-to-Any • Updated Oct 24, 2024 • 114 • 285 sesame/csm-1b Text-to-Speech • 2B • Updated Dec 1, 2025 • 303k • 2.4k HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation Paper • 2505.04512 • Published May 7, 2025 • 36
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation Paper • 2505.04512 • Published May 7, 2025 • 36
Scaling test time compute 1B > 405B! Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper • 2502.05171 • Published Feb 7, 2025 • 158
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper • 2502.05171 • Published Feb 7, 2025 • 158
