OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas Paper β’ 2501.15427 β’ Published 4 days ago β’ 4
DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation Paper β’ 2501.16764 β’ Published 2 days ago β’ 13
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training Paper β’ 2501.17161 β’ Published 1 day ago β’ 36
Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation Paper β’ 2501.15907 β’ Published 3 days ago β’ 14
Towards General-Purpose Model-Free Reinforcement Learning Paper β’ 2501.16142 β’ Published 3 days ago β’ 19
view article Article Hunyuan video LoRA training study (Single image/style training) By neph1 β’ 3 days ago β’ 1