>mfw Research news

07/12/2025

>ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation
https://arxiv.org/abs/2507.07317

>TalkFashion: Intelligent Virtual Try-On Assistant Based on Multimodal Large Language Model
https://arxiv.org/abs/2507.05790

>Fair Domain Generalization: An Information-Theoretic View
https://arxiv.org/abs/2507.05823

>Rethinking Layered Graphic Design Generation with a Top-Down Approach
https://arxiv.org/abs/2507.05601

>ReLayout: Integrating Relation Reasoning for Content-aware Layout Generation with Multi-modal Large Language Models
https://arxiv.org/abs/2507.05568

>OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts
https://arxiv.org/abs/2507.05427

>Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration
https://arxiv.org/abs/2507.05604

>Critiques of World Models
https://arxiv.org/abs/2507.05169

>MoDiT: Learning Highly Consistent 3D Motion Coefficients with Diffusion Transformer for Talking Head Generation
https://arxiv.org/abs/2507.05092

>EXPOTION: Facial Expression and Motion Control for Multimodal Music Generation
https://arxiv.org/abs/2507.04955

>ZERO: Multi-modal Prompt-based Visual Grounding
https://arxiv.org/abs/2507.04270

>SeqTex: Generate Mesh Textures in Video Sequence
https://arxiv.org/abs/2507.04285

>PromptSR: Cascade Prompting for Lightweight Image Super-Resolution
https://arxiv.org/abs/2507.04118

>Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learning
https://arxiv.org/abs/2507.04020

>EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation
https://arxiv.org/abs/2507.03905