285 citations · 736 across the 85 of their papers we have counts for
87 papers
Look Before You Restore: Learning to Predict Before Acting for Agentic Image Restoration
Xu Zhang, Jun Wan, Lefei Zhang +1
Agents for mixed-degradation image restoration typically learn what a tool does to an image only after running it: failed calls waste computation and harmful outputs go unnoticed u…
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…
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…
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…
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…
CtrlAttack: A Unified Attack on World-Model Control in Diffusion Models
Shuhan Xu, Siyuan Liang, Hongling Zheng +4
Diffusion-based image-to-video (I2V) models increasingly exhibit world-model-like properties by implicitly capturing temporal dynamics. However, existing studies have mainly focuse…
FedEU: Evidential Uncertainty-Driven Federated Fine-Tuning of Vision Foundation Models for Remote Sensing Image Segmentation
Xiaokang Zhang, Xuran Xiong, Jianzhong Huang +1
Remote sensing image segmentation (RSIS) in federated environments has gained increasing attention because it enables collaborative model training across distributed datasets witho…
SIGMAE: A Spectral-Index-Guided Foundation Model for Multispectral Remote Sensing
Xiaokang Zhang, Bo Li, Chufeng Zhou +2
Pretraining and fine-tuning have emerged as a new paradigm in remote sensing image interpretation. Among them, Masked Autoencoder (MAE)-based pretraining stands out for its strong…
DSA-SRGS: Super-Resolution Gaussian Splatting for Dynamic Sparse-View DSA Reconstruction
Shiyu Zhang, Zhicong Wu, Huangxuan Zhao +7
Digital subtraction angiography (DSA) is a key imaging technique for the auxiliary diagnosis and treatment of cerebrovascular diseases. Recent advancements in gaussian splatting an…
SongSong: A Time Phonograph for Chinese SongCi Music from Thousand of Years Away
Jiajia Li, Jiliang Hu, Ziyi Pan +4
Recently, there have been significant advancements in music generation. However, existing models primarily focus on creating modern pop songs, making it challenging to produce anci…
UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation
Ruiheng Zhang, Jingfeng Yao, Huangxuan Zhao +9
Despite recent progress, medical foundation models still struggle to unify visual understanding and generation, as these tasks have inherently conflicting goals: semantic abstracti…
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…
OFL-SAM2: Prompt SAM2 with Online Few-shot Learner for Efficient Medical Image Segmentation
Meng Lan, Lefei Zhang, Xiaomeng Li
The Segment Anything Model 2 (SAM2) has demonstrated remarkable promptable visual segmentation capabilities in video data, showing potential for extension to medical image segmenta…
TGC-Net: A Structure-Aware and Semantically-Aligned Framework for Text-Guided Medical Image Segmentation
Gaoren Lin, Huangxuan Zhao, Yuan Xiong +3
Text-guided medical segmentation enhances segmentation accuracy by utilizing clinical reports as auxiliary information. However, existing methods typically rely on unaligned image…
EvoIR: Towards All-in-One Image Restoration via Evolutionary Frequency Modulation
Jiaqi Ma, Shengkai Hu, Xu Zhang +4
All-in-One Image Restoration (AiOIR) tasks often involve diverse degradation that require robust and versatile strategies. However, most existing approaches typically lack explicit…
DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
Jialv Zou, Shaoyu Chen, Bencheng Liao +6
Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse, tending to generate conservative and homogeneous behaviors. While DiffusionDrive empl…
ClusIR: Towards Cluster-Guided All-in-One Image Restoration
Shengkai Hu, Jiaqi Ma, Xu Zhang +3
All-in-One Image Restoration (AiOIR) aims to recover high-quality images from diverse degradations within a unified framework. However, existing methods often fail to explicitly mo…
Neural Discrete Representation Learning for Sparse-View CBCT Reconstruction: From Algorithm Design to Prospective Multicenter Clinical Evaluation
Haoshen Wang, Lei Chen, Wei-Hua Zhang +13
Cone beam computed tomography (CBCT)-guided puncture has become an established approach for diagnosing and treating early- to mid-stage thoracic tumours, yet the associated radiati…
Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios
Luohe Shi, Zuchao Li, Lefei Zhang +3
Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typical…
ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
Zhiyu Zheng, Shaoyu Chen, Haoran Yin +5
End-to-end autonomous driving (E2EAD) systems, which learn to predict future trajectories directly from sensor data, are fundamentally challenged by the inherent spatio-temporal im…
ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models
Jiani Guo, Zuchao Li, Jie Wu +5
Large Language Models (LLMs), constrained by limited context windows, often face significant performance degradation when reasoning over long contexts. To address this, Retrieval-A…
Proto-Former: Unified Facial Landmark Detection by Prototype Transformer
Shengkai Hu, Haozhe Qi, Jun Wan +4
Recent advances in deep learning have significantly improved facial landmark detection. However, existing facial landmark detection datasets often define different numbers of landm…
Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking
Yuchun Miao, Liang Ding, Sen Zhang +3
Despite the success of Reinforcement Learning from Human Feedback (RLHF) in aligning language models with human values, reward hacking-or reward over-optimization-remains a major c…
A Multi-Language Object-Oriented Programming Benchmark for Large Language Models
Shuai Wang, Liang Ding, Li Shen +4
Establishing fair and robust benchmarks is essential for evaluating intelligent code generation by large language models (LLMs). Our survey of 35 existing benchmarks uncovers three…