🏢 ByteDance

PeRFlow accelerates diffusion models by straightening their sampling trajectories using a piecewise reflow operation, enabling fast and high-quality image generation with minimal computational cost.

PaDeLLM-NER massively accelerates LLM-based NER inference by up to 10x, enabling near real-time performance without accuracy loss.

Leveraging image understanding models for image tokenizer training dramatically boosts image generation quality, achieving state-of-the-art results.

Hyper-SD boosts diffusion model speed by using trajectory segmented consistency distillation and human feedback, achieving state-of-the-art performance.

HumanSplat: single image-based 3D human reconstruction using Gaussian Splatting with structural priors, achieving state-of-the-art quality and speed.

DeTeCtive: a novel multi-task contrastive learning framework, achieves state-of-the-art AI-generated text detection by distinguishing diverse writing styles instead of simple binary classification.

Image generation gets a speed boost with TiTok, a novel 1D image tokenizer that uses just 32 tokens for high-quality image reconstruction and generation, achieving up to 410x faster processing than st…

DiMR boosts image generation fidelity by cleverly combining multi-resolution networks with time-dependent layer normalization in diffusion models, achieving state-of-the-art results on ImageNet.