activity
20242026
collaborators

46 papers

cs.CV2026

ClusIR: Towards Cluster-Guided All-in-One Image Restoration

Shengkai Hu, Jiaqi Ma, Xu Zhang +3

ClusIR introduces a cluster-guided framework that learns degradation semantics via clustering and uses these cues to adaptively restore images across spatial and frequency domains.

cs.CL2026

From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons

Xiangyu Ma, Teng Xiao, Zuchao Li +1

Diffusion models promise efficient parallel text generation but rely on bidirectional attention, creating a structural mismatch with pre-trained Autoregressive (AR) models. This in…

cs.LG2026

When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR

Yuchun Miao, Sen Zhang, Yuqi Zhang +4

Reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for advanced reasoning in Large Language Models (LLMs), but rollout samples are expensive to…

cs.CV2026

LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

Xiang Chen, Hao Li, Jiangxin Dong +54

This paper presents a review for the LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aimed to advance research on real-world all-in-one image restoration…

cs.CL2026

RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding

Zihong Zhang, Zuchao Li, Lefei Zhang +2

Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-v…

cs.CV2026

ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration

Xu Zhang, Huan Zhang, Guoli Wang +2

All-in-One Image Restoration (AiOIR) has advanced significantly, offering promising solutions for complex real-world degradations. However, most existing approaches rely heavily on…