activity
20242026
collaborators

5 papers

cs.AI2026

Multi-modal Reasoning with LLMs for Visual Semantic Arithmetic

Chuou Xu, Liya Ji, Qifeng Chen

Reinforcement learning (RL) as post-training is crucial for enhancing the reasoning ability of large language models (LLMs) in coding and math. However, their capacity for visual s…

cs.CV2026

Instruction-based Image Editing with Planning, Reasoning, and Generation

Liya Ji, Chenyang Qi, Qifeng Chen

Editing images via instruction provides a natural way to generate interactive content, but it is a big challenge due to the higher requirement of scene understanding and generation…

cs.CV2025

Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising

Yifan Wang, Liya Ji, Zhanghan Ke +3

We propose an approach to enhancing synthetic video realism, which can re-render synthetic videos from a simulator in photorealistic fashion. Our realism enhancement approach is a…

cs.MM2025

VAInpaint: Zero-Shot Video-Audio inpainting framework with LLMs-driven Module

Kam Man Wu, Zeyue Tian, Liya Ji +1

Video and audio inpainting for mixed audio-visual content has become a crucial task in multimedia editing recently. However, precisely removing an object and its corresponding audi…

cs.CV2024

ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement

Zhefan Rao, Liya Ji, Yazhou Xing +6

Text-to-video (T2V) generation has gained significant attention recently. However, the costs of training a T2V model from scratch remain persistently high, and there is considerabl…