2025-01-16s

XMusic: A new framework generates high-quality, emotionally controllable symbolic music from various prompts (images, videos, text, tags, humming).

Machine learning models can enable secure computations previously impossible with cryptography, achieving privacy and efficiency in Trusted Capable Model Environments (TCMEs).

RepVideo enhances text-to-video generation by enriching feature representations, resulting in significantly improved temporal coherence and spatial detail.

Ouroboros-Diffusion: A novel tuning-free long video generation framework achieving unprecedented content consistency by cleverly integrating information across frames via latent sampling, cross-frame…

Multimodal LLMs can now evaluate art aesthetics with human-level accuracy using a novel dataset (MM-StyleBench) and prompt method (ArtCoT), significantly improving AI alignment in artistic evaluation.

MMDocIR, a new benchmark dataset, enables better evaluation of multi-modal document retrieval systems by providing page-level and layout-level annotations for diverse long documents and questions.

CityDreamer4D generates realistic, unbounded 4D city models by cleverly separating dynamic objects (like vehicles) from static elements (buildings, roads), using multiple neural fields for enhanced re…

Parameter-Inverted Image Pyramid Networks (PIIP) drastically cut visual model computing costs without sacrificing accuracy by using smaller models for higher-resolution images and larger models for lo…