Fan Ma

LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization

ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation

MoDE: Weight Denoising Towards Better LLM Performance through a Mixture of Domain Experts

Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time

BrainMoE: Towards Universal EEG Foundation Models with Channel-wise Mixture-of-Experts

StrucBooth: Structural Gradient Supervised Tuning for Enhanced Portrait Animation

DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization

Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection

Adversarial-Guided Diffusion for Robust and High-Fidelity Multimodal LLM Attacks

Generalization by Specialization: Unveiling Specialized Subnetworks in Large Language Models

Free-MoE: Tuning-Free Mixture-of-Experts Purifying LLMs to Thrive across Any Field