7 papers
MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation
Yiming Zeng, Lei Lu, Zexin Li +9
Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of large language models, but existing MoE-based PEFT methods typically improve capacity by storing multiple ful…
I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications
Dasen Dai, Biao Wu, Meng Fang +2
Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, existing document agents mainly trans…
UIPress: Bringing Optical Token Compression to UI-to-Code Generation
Dasen Dai, Shuoqi Li, Ronghao Chen +3
UI-to-Code generation requires vision-language models (VLMs) to produce thousands of tokens of structured HTML/CSS from a single screenshot, making visual token efficiency critical…
GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models
Zhankai Ye, Bofan Li, Yukai Jin +5
Discrete motion tokenization has recently enabled Large Language Models (LLMs) to serve as versatile backbones for motion understanding and motion-language reasoning. However, exis…
Classroom Final Exam: An Instructor-Tested Reasoning Benchmark
Chongyang Gao, Diji Yang, Shuyan Zhou +4
We introduce CFE-Bench (Classroom Final Exam), a multimodal benchmark for evaluating the reasoning capabilities of large language models across more than 20 STEM domains. CFE-Bench…
ComUICoder: Component-based Reusable UI Code Generation for Complex Websites via Semantic Segmentation and Element-wise Feedback
Jingyu Xiao, Jiantong Qin, Shuoqi Li +5
Multimodal Large Language Models (MLLMs) have demonstrated strong performance on the UI-to-code task, which aims to generate UI code from design mock-ups. However, when applied to…