We study how to apply large language models to write grounded and organized long-form articles from scratch, with comparable breadth and depth to Wikipedia pages.
We try to narrow the gap by mining the potential of VLMs for better performance and any-to-any workflow from three aspects, i. e., high-resolution visual tokens, high-quality data, and VLM-guided generation.
Ranked #8 on Visual Question Answering on MM-Vet
We present InstantMesh, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability.
We present the LM Transparency Tool (LM-TT), an open-source interactive toolkit for analyzing the internal workings of Transformer-based language models.
We propose Magic Clothing, a latent diffusion model (LDM)-based network architecture for an unexplored garment-driven image synthesis task.
However, most existing data profiling systems that focus on complex statistics do not provide proper integration with the tools used by contemporary data scientists.
The quadratic complexity and weak length extrapolation of Transformers limits their ability to scale to long sequences, and while sub-quadratic solutions like linear attention and state space models exist, they empirically underperform Transformers in pretraining efficiency and downstream task accuracy.
Large-scale recommendation systems are characterized by their reliance on high cardinality, heterogeneous features and the need to handle tens of billions of user actions on a daily basis.
Ranked #1 on Recommendation Systems on MovieLens 20M (HR@10 (full corpus) metric)
To overcome their inherent incompleteness, multi-modal knowledge graph completion (MMKGC) aims to discover unobserved knowledge from given MMKGs, leveraging both structural information from the triples and multi-modal information of the entities.
We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard raster-scan "next-token prediction".
Ranked #7 on Image Generation on ImageNet 256x256