publications

Selected and full publications in reverse chronological order.

2026

  1. geosvg-rl.png
    GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation
    Sifan Li, Yujun Cai, Hongkai Chen, and 1 more author
    2026
    arXiv
  2. optisql.png
    OptiSQL: Executable SQL Generation from Optical Tokens
    Sifan Li, Hongkai Chen, Yujun Cai, and 3 more authors
    2026
    arXiv
  3. MMIFN: A Multi-Modal Interactive Fusion Network for Omnidirectional Image Quality Assessment
    Yun Liu, Sifan Li, Huiyu Duan, and 2 more authors
    IEEE Transactions on Multimedia, 2026
    Early Access. First student author.
    DOI
  4. TFFN: Three-Branch Feature Fusion Network for Stereoscopic Omnidirectional Image Quality Assessment
    Yun Liu, Sifan Li, Daoxin Fan, and 2 more authors
    IEEE Transactions on Multimedia, 2026
    Early Access. First student author.
    DOI
  5. AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoning
    Liyang Chen, Hongkai Chen, Yujun Cai, and 3 more authors
    2026
    arXiv

2025

  1. semvink.png
    SemVink: Advancing VLMs’ Semantic Understanding of Optical Illusions via Visual Global Thinking
    Sifan Li, Yujun Cai, and Yiwei Wang
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
    Oral presentation in the Main Conference of EMNLP 2025.
    PDF Poster Slides Website
  2. logos.png
    Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector
    Sifan Li, Hongkai Chen, Yujun Cai, and 4 more authors
    2025
    arXiv PDF Website
  3. cpm.png
    Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs
    Sifan Li, Yujun Cai, Bryan Hooi, and 2 more authors
    2025
    arXiv PDF Poster Website
  4. replace.png
    Replace in Translation: Boost Concept Alignment in Counterfactual Text-to-Image
    Sifan Li, Ming Tao, Hao Zhao, and 2 more authors
    2025
    arXiv PDF Poster
  5. Detecting and Mitigating Insertion Hallucination in Video-to-Audio Generation
    Liyang Chen, Hongkai Chen, Yujun Cai, and 3 more authors
    2025
    arXiv
  6. BPGI: A Brain-Perception Guided Interactive Network for Stereoscopic Omnidirectional Image Quality Assessment
    Yun Liu, Sifan Li, Zihan Liu, and 2 more authors
    IEEE Open Journal on Immersive Displays, 2025
    First student author.
    DOI
  7. Multi-Task Guided No-Reference Omnidirectional Image Quality Assessment With Feature Interaction
    Yun Liu, Sifan Li, Huiyu Duan, and 3 more authors
    IEEE Transactions on Circuits and Systems for Video Technology, 2025
    First student author.
    DOI

2024

  1. Image Aesthetics Assessment Based on Visual Perception and Textual Semantic Understanding
    Yun Liu, Zhipeng Wen, Sifan Li, and 2 more authors
    In Digital Multimedia Communications, 2024
    DOI
  2. A Multimodal Fake News Detection Model with Self-supervised Unimodal Label Generation
    Yun Liu, Zhipeng Wen, Minzhu Jin, and 5 more authors
    In Advanced Intelligent Computing Technology and Applications, 2024
    DOI