papers

Publications (9)

cs.CV2026

Factuality Matters: When Image Generation and Editing Meet Structured Visuals

Le Zhuo, Songhao Han, Yuandong Pu +8

While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and…

cs.RO2025

RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation

Songhao Han, Boxiang Qiu, Yue Liao +4

Recent advances in vision-language models (VLMs) have enabled instruction-conditioned robotic systems with improved generalization. However, most existing work focuses on reactive…

cs.IR2022

VLSNR:Vision-Linguistics Coordination Time Sequence-aware News Recommendation

Songhao Han, Wei Huang, Xiaotian Luan

News representation and user-oriented modeling are both essential for news recommendation. Most existing methods are based on textual information but ignore the visual information…

cs.CV2025

Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency

Hongyu Li, Songhao Han, Yue Liao +4

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large langua…

cs.CV2024

LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions

Songhao Han, Le Zhuo, Yue Liao +1

Vision-language models (VLMs) offer a promising paradigm for image classification by comparing the similarity between images and class embeddings. A critical challenge lies in craf…

cs.CV2026

PICABench: How Far Are We from Physically Realistic Image Editing?

Yuandong Pu, Le Zhuo, Songhao Han +10

Image editing has achieved remarkable progress recently. Modern editing models could already follow complex instructions to manipulate the original content. However, beyond complet…

cs.CV2023

Video Background Music Generation: Dataset, Method and Evaluation

Le Zhuo, Zhaokai Wang, Baisen Wang +7

Music is essential when editing videos, but selecting music manually is difficult and time-consuming. Thus, we seek to automatically generate background music tracks given video in…

eess.IV2024

Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation

Hairong Shi, Songhao Han, Shaofei Huang +6

Tumor lesion segmentation on CT or MRI images plays a critical role in cancer diagnosis and treatment planning. Considering the inherent differences in tumor lesion segmentation da…

cs.CV2024

VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

Songhao Han, Wei Huang, Hairong Shi +7

The advancement of Large Vision Language Models (LVLMs) has significantly improved multimodal understanding, yet challenges remain in video reasoning tasks due to the scarcity of h…