5 papers
UniER: A Unified Benchmark for Item-level and Path-level Exercise Recommendation
Xinghe Cheng, Guiyong Zhuang, Yusheng Xie +5
Personalized exercise recommendation dynamically aligns pedagogical resources with individual knowledge mastery, which is crucial for satisfying students' dynamic learning needs in…
ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models
Chao Zeng, Songwei Liu, Yusheng Xie +6
Large Language Models (LLMs) have revolutionized natural language processing tasks. However, their practical application is constrained by substantial memory and computational dema…
Efficient Scaling of Diffusion Transformers for Text-to-Image Generation
Hao Li, Shamit Lal, Zhiheng Li +9
We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training…
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Hossein Aboutalebi, Hwanjun Song, Yusheng Xie +7
Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs. Previous…
Diffusion Soup: Model Merging for Text-to-Image Diffusion Models
Benjamin Biggs, Arjun Seshadri, Yang Zou +6
We present Diffusion Soup, a compartmentalization method for Text-to-Image Generation that averages the weights of diffusion models trained on sharded data. By construction, our ap…