🏢 ByteDance

Video Depth Anything achieves consistent depth estimation for super-long videos by enhancing Depth Anything V2 with a spatial-temporal head and a novel temporal consistency loss, setting a new state-o…

ToolHop: New benchmark dataset rigorously evaluates LLMs’ multi-hop tool use, revealing significant challenges and variations across different LLM families.

Infinity, a novel bitwise autoregressive model, sets new records in high-resolution image synthesis, outperforming top diffusion models in speed and quality.

AnyDressing: Customizable multi-garment virtual dressing via a novel latent diffusion model!

TokenFlow: One image tokenizer, mastering both visual understanding & generation!

UltraMem, a novel ultra-sparse memory network, drastically speeds up LLM inference by 6x compared to MoE while maintaining performance, paving the way for efficient large-scale model deployment.

Randomized Autoregressive Modeling (RAR) sets a new state-of-the-art in image generation by cleverly introducing randomness during training to improve the model’s ability to learn from bidirectional c…