15 papers
GUI-AC: Enhancing Continual Learning in GUI Agents
Can Lin, Tao Feng, Hangjie Yuan +3
Graphical User Interfaces (GUIs) serve as the dominant medium for human-computer interaction, yet building GUI agents that generalize across the vast diversity of real-world interf…
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
Jiazheng Xing, Hangjie Yuan, Lingling Cai +9
Connector-based video unified models have demonstrated strong capability in instruction-grounded video synthesis, but integrating a large high-fidelity generator into the unified t…
5% > 100%: Flatness Preference is All You Need for Multimodal Parameter-Efficient Fine-Tuning
Yifan Zhu, Can Lin, Hangjie Yuan +4
Parameter-Efficient Fine-Tuning (PEFT) methods provide a streamlined and efficient tool for adapting large models to domain-specific multimodal downstream tasks. Although these met…
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
Yuying Li, Leqi Zheng, Yongzi Yu +6
On-Policy distillation (OPD) in large language models is shifting from full-trace KL supervision toward more selective training paradigms. Recent OPD methods increasingly focus on…
MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
Shuhang Chen, Hangjie Yuan, Yunqiu Xu +5
Despite strong results on many tasks, multimodal large language models (MLLMs) still underperform on visual mathematical problem solving, especially in reliably perceiving and inte…
A Faster Path to Continual Learning
Wei Li, Hangjie Yuan, Zixiang Zhao +3
Continual Learning (CL) aims to train neural networks on a dynamic stream of tasks without forgetting previously learned knowledge. Among optimization-based approaches, C-Flat has…