5 papers
Allo{SR}: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows
Zihan Wang, Xudong Huang, Junbo Qiao +4
Real-world image super-resolution (Real-SR) has been revolutionized by leveraging the powerful generative priors from Diffusion Models (DMs) and Flow Matching (FM). However, existi…
From Sequential to Spatial: Reordering Autoregression for Efficient Visual Generation
Siyang Wang, Hanting Li, Wei Li +3
Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token…
DSPO: Direct Semantic Preference Optimization for Real-World Image Super-Resolution
Miaomiao Cai, Simiao Li, Wei Li +4
Recent advances in diffusion models have improved Real-World Image Super-Resolution (Real-ISR), but existing methods lack human feedback integration, risking misalignment with huma…
CBQ: Cross-Block Quantization for Large Language Models
Xin Ding, Xiaoyu Liu, Zhijun Tu +8
Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs. However, existing PTQ methods only focus on handling the ou…
GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization
Yirui Chen, Xudong Huang, Quan Zhang +9
The extraordinary ability of generative models emerges as a new trend in image editing and generating realistic images, posing a serious threat to the trustworthiness of multimedia…