Tag
A virtual creature trained with reinforcement learning has been given fur and sound, with the sound generated directly from neural network activations. Trained using JAX and MuJoCo, and rendered with three.js and WebGPU, it presents a realistic effect of crawling on the floor, blending art and research.
MultiHashFormer is a hash-based generative language model that represents each token as a unique hash signature, enabling parameter-efficient autoregression. It outperforms standard Transformer LMs at 100M, 1B, and 3B scales and supports multilingual vocabulary expansion without increasing parameters.
SwiftVR is a real-time one-step generative video restoration framework that achieves high frame rates on consumer GPUs using efficient attention mechanisms and a lightweight restoration-aware autoencoder.
γ-World is a generative multi-agent world model that supports independently controllable, permutation-symmetric agents using Simplex Rotary Agent Encoding and Sparse Hub Attention, achieving real-time 24 FPS rollouts and zero-shot generalization from two to four players.