Author

Jun-Gang Li

h-index 10 View on Semantic Scholar

We have 3 of 30 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation

Recent video generation models can produce highly realistic videos from natural language instructions, with visual quality approaching cinematic standards. Existing evaluation benchmarks, however, predominantly assess visual quality, aesthetic appeal and physical plausibility, while paying limited attention to text, an...

Yu Huang, Jun-Gang Li, Zhiyuan Wang et al. · 0 citations

#artificial intelligence Apr 2026

Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation

A systematic analysis of expert routing patterns in MoE models reveals Language Routing Isolation, in which high- and low-resource languages tend to activate largely disjoint expert sets, and proposes RISE, a framework that exploits routing isolation to identify and adapt language-specific expert subnetworks.

Kening Zheng, Wei-Chieh Huang, Jiahao Huo et al. · arXiv.org · 4 citations · ⚡2

Preprint Aug 2026

Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning

Across counter-commonsense visual benchmarks, TACT substantially improves visual reasoning while preserving general capabilities, demonstrating effective text-to-vision cross-modal transfer.

Chen Ling, Hanqian Li, Dong-Nan Liu et al. · 1 citation