>mfw Research news

10/13/2025

>Efficient Bayesian Inference from Noisy Pairwise Comparisons
https://arxiv.org/abs/2510.09333

>Training Feature Attribution for Vision Models
https://arxiv.org/abs/2510.09135

>Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation
https://arxiv.org/abs/2510.09094

>MCMC: Bridging Rendering, Optimization and Generative AI
https://sinbag.github.io/mcmc

>OSCAR: Orthogonal Stochastic Control for Alignment-Respecting Diversity in Flow Matching
https://arxiv.org/abs/2510.09060

>Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
https://arxiv.org/abs/2510.09012

>On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
https://arxiv.org/abs/2510.09008

>Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
https://arxiv.org/abs/2510.08994

>Creation, Critique, and Consumption: Exploring Generative AI Descriptions for Supporting Blind and Low Vision Professionals with Visual Tasks
https://arxiv.org/abs/2510.08991

>D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models
https://arxiv.org/abs/2510.09473

>Vision Language Models: Survey of 26K Papers
https://arxiv.org/abs/2510.09586

>TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
https://arxiv.org/abs/2510.09561

>Few-shot multi-token DreamBooth with LoRa for style-consistent character generation
https://arxiv.org/abs/2510.09475

>HandEval: Taking the First Step Towards Hand Quality Evaluation in Generated Images
https://arxiv.org/abs/2510.08978

>SkipSR: Faster Super Resolution with Token Skipping
https://rccchoudhury.github.io/skipsr

>LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution
https://arxiv.org/abs/2510.08771

>FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
https://arxiv.org/abs/2510.08669