Junyu Gao

TeleAI, Northwestern Polytechnical University

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Computer Vision (2)Multimodal Models (2)Code Generation & Program Synthesis (1)

Frequent co-authors

Feiyu Wang (1)Jiayuan Yang (1)Zhiyuan Zhao (1)Da Zhang (1)

Papers (2)

Mar 10, 2026

2d ago·also Fudan, TeleAI

IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework

By having a single VLM critique its own SVG renderings, IntroSVG learns to generate more complex, semantically aligned, and editable vector graphics from text prompts.

Feiyu Wang, Jiayuan Yang, Zhiyuan Zhao +4

Code Generation & Program Synthesis Computer Vision Multimodal Models

Feb 26, 2026

2w ago·also Northwestern, TeleAI

HulluEdit: Single-Pass Evidence-Consistent Subspace Editing for Mitigating Hallucinations in Large Vision-Language Models

By surgically removing "hallucination patterns" from a model's hidden state, HulluEdit offers a reference-free, single-pass method to dramatically reduce object hallucinations in LVLMs without sacrificing visual grounding.

Yang-Sen Lin, Yangguang Lin, Quan Fang +8

Computer Vision Multimodal Models

Search

Junyu Gao

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)