Geekom produces some premium products at not-so-premium prices, and the X16 model is no exception. Here's how it's fared after weeks of usage.

We propose TraceRL, a trajectory-aware reinforcement learning method for diffusion language models, which demonstrates the best performance among RL approaches for DLMs. We also introduce a ...

F5-TTS-Emotion-CFG introudces explicit emotion conditioning in F5-TTS zero-shot voice cloning model, by fine-tuning on ESD dataset. The following emotions are ...