5 papers
UNIVID: Unified Vision-Language Model for Video Moderation
Kejuan Yang, Yizhuo Zhang, Mingyuan Du +6
Global-scale video moderation faces a dual challenge: the need for fine-grained multi-modal reasoning and the demand for interpretable outputs to support downstream enforcement. Tr…
Looks Right, Works Right: A Project-Level Benchmark for Multi-Screen Mobile App Generation
Fan Wu, Cuiyun Gao, Yiming Huang +3
Recent multimodal large language models can convert visual designs directly into executable code, but real mobile products require multiple screenshots to become a buildable codeba…
Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages
Fan Wu, Lishuai Dong, Cuiyun Gao +4
Recent advancements in multimodal large language models (MLLMs) have achieved remarkable progress in multimodal reasoning and code generation, catalyzing a new paradigm for front-e…
SPVR: syntax-to-prompt vulnerability repair based on large language models
Ruoke Wang, Zongjie Li, Cuiyun Gao +3
Purpose: In the field of vulnerability repair, previous research has leveraged pretrained models and LLM-based prompt engineering, among which LLM-based approaches show better gene…
Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data
Xin-Cheng Wen, Yijun Yang, Cuiyun Gao +2
Large language models (LLMs) demonstrate considerable proficiency in numerous coding-related tasks; however, their capabilities in detecting software vulnerabilities remain limited…