影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
90.31/100
前 0.6%
全站排名 #356
发表论文22 篇
平均评分
年均产出7.3 篇/年
Lei Zhang
研究方向
Computer vision · image processing · pattern recognition · deep learning · Control theory · signal processing · wavelet transform
24
Many-for-Many: Unify the Training of Multiple Video and Image Generation and Manipulation Tasks
ICLR 2026Poster
通讯26
One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image
ICLR 2026Poster
通讯4
VideoVerse: How Far is Your T2V Generator from a World Model?
ICLR 2026Withdrawn
通讯5
Pretraining a Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm
ICLR 2026Withdrawn
三作5
VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding
ICLR 2026Withdrawn
5
TIIF-Bench: How Does Your T2I Model Follow Your Instructions?
ICLR 2026Withdrawn
通讯17
Polyline Path Masked Attention for Vision Transformer
NeurIPS 2025Spotlight
24
DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
NeurIPS 2025Spotlight
通讯24
VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
NeurIPS 2025Spotlight
23
InstructRestore: Region-Customized Image Restoration with Human Instructions
NeurIPS 2025Poster
通讯24
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion
ICLR 2025Poster
通讯19
GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
NeurIPS 2025Poster
通讯26
One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
NeurIPS 2025Poster
通讯22
MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
NeurIPS 2025Poster
通讯29
DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
NeurIPS 2025Poster
通讯21
Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning
ICLR 2025Poster
三作19
Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos
NeurIPS 2025Poster
30
FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling
ICLR 2025Poster
三作26
Toward Generalizing Visual Brain Decoding to Unseen Subjects
ICLR 2025Poster
通讯