>mfw MORE Research news

>MMLongCite: A Benchmark for Evaluating Fidelity of Long-Context Vision-Language Models
https://arxiv.org/abs/2510.13276

>End-to-End Multi-Modal Diffusion Mamba
https://arxiv.org/abs/2510.13253

>Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
https://map-the-flow.github.io

>Prompt-based Adaptation in Large-scale Vision Models: A Survey
https://arxiv.org/abs/2510.13219

>LOTA: Bit-Planes Guided AI-Generated Image Detection
https://arxiv.org/abs/2510.14230

>Towards Reversible Model Merging For Low-rank Weights
https://arxiv.org/abs/2510.14163

>NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations
https://arxiv.org/abs/2510.14025

>Generative Universal Verifier as Multimodal Meta-Reasoner
https://arxiv.org/abs/2510.13804

>Adaptive Visual Conditioning for Semantic Consistency in Diffusion-Based Story Continuation
https://arxiv.org/abs/2510.13787

>Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter
https://arxiv.org/abs/2510.13419

>CanvasMAR: Improving Masked Autoregressive Video Generation With Canvas
https://arxiv.org/abs/2510.13669

>Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
https://arxiv.org/abs/2510.13418

>Edit-Your-Interest: Efficient Video Editing via Feature Most-Similar Propagation
https://arxiv.org/abs/2510.13084

>CADE 2.5 - ZeResFDG: Frequency-Decoupled, Rescaled and Zero-Projected Guidance for SD/SDXL Latent Diffusion Models
https://arxiv.org/abs/2510.12954

>Counting Hallucinations in Diffusion Models
https://arxiv.org/abs/2510.13080

>SeqBench: Benchmarking Sequential Narrative Generation in Text-to-Video Models
https://videobench.github.io/SeqBench.github.io

>Synthetic History: Evaluating Visual Representations of the Past in Diffusion Models
https://arxiv.org/abs/2505.17064

>CAP: Evaluation of Persuasive and Creative Image Generation
https://arxiv.org/abs/2412.10426