collaborators

8 papers

cs.CV2026

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…

cs.CV2026

MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts

Nuoyan Zhou, Zhijun Tu, Lei Yu +4

Visual AutoRegressive modeling (VAR) has pioneered a coarse-to-fine multi-scale autoregressive generative paradigm, demonstrating strong capabilities in image generation. However,…

cs.CV2026

CSD: Content-aware Speculative Decoding for Efficient Image Generation

Mingcheng Wang, Junbo Qiao, Yunchen Li +8

Speculative decoding (SD) has emerged as a key solution to accelerate the inference of autoregressive models. However, in the field of image generation, it faces the challenge of l…

cs.LG2026

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression

Yuntian Tang, Bohan Jia, Wenxuan Huang +7

Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computational overhead for inference. E…

cs.CV2026

RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought

Junbo Qiao, Miaomiao Cai, Wei Li +5

Real-World Image Super-Resolution is one of the most challenging task in image restoration. However, existing methods struggle with an accurate understanding of degraded image cont…

eess.IV2026

RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration

Yan Chen, Yi Wen, Wei Li +4

We present the RAW domain diffusion model (RDDM), an end-to-end diffusion model that restores photo-realistic images directly from the sensor RAW data. While recent sRGB-domain dif…