Humphrey Shi

63 papers · 2021–2026 · 7 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (7) 🐝 Cross-Pollinator (10) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🗺️ Taxonomy Completionist (91) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (7) 🏃 Academic Marathon (5) 🏠 Conference Loyalist (23) 🤝 Dynamic Duo (15) 👥 Mega-Team (20) 🔬 Deep Specialist (12) 🧬 Topic Evolution ⚡ Prolific Year (19) 💎 Century Club (63) 🔥 Unstoppable (6) 🗃️ Keyword Collector (252)

Conferences

CVPR (23) WACV (12) ICCV (9) ECCV (6) NIPS (5) AAAI (4) ICLR (4)

Top co-authors

Zhangyang Wang (15) Xingqian Xu (13) Shant Navasardyan (12) Gao Huang (9) Yunchao Wei (8) Kai Wang (7) Jiachen Li (6) Yao Zhao (6) Ali Hassani (6) Vidit Goel (5)

Keywords

diffusion model (12) text-to-image generation (6) semantic segmentation (6) image generation (5) domain adaptation (5) model compression (5) attention mechanism (4) multimodal learning (4) object detection (4) image inpainting (4) instance segmentation (4) generative model (4) generative adversarial network (3) vision-language model (3) transformer architecture (3) image editing (3) style transfer (3) efficient computing (3) vision transformer (2) semi-supervised learning (2)

Papers

Beyond Realism: Learning the Art of Expressive Composition with StickerNet WACV 2026

Safe Vision-Language Models via Unsafe Weights Manipulation WACV 2026

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text CVPR 2025

Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment CVPR 2025

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders ICLR 2025

ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance ICLR 2025

HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models ICLR 2025

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance ICCV 2025

CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting ICCV 2025

T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation ICCV 2025

HyPiDecoder: Hybrid Pixel Decoder for Efficient Segmentation and Detection ICCV 2025

VCoder: Versatile Vision Encoders for Multimodal Large Language Models CVPR 2024

FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models NIPS 2024

Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level NIPS 2024

CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts NIPS 2024

Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models CVPR 2024

Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis CVPR 2024

Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models CVPR 2024

PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor CVPR 2024

OpenBias: Open-set Bias Detection in Text-to-Image Generative Models CVPR 2024

Brush2Prompt: Contextual Prompt Generator for Object Inpainting CVPR 2024

Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation ECCV 2024

Benchmarking Object Detectors with COCO: A New Path Forward ECCV 2024

Diffusion for Natural Image Matting ECCV 2024

Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community ICLR 2024

FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude WACV 2024

Video Instance Matting WACV 2024

Continuous Adaptation for Interactive Segmentation Using Teacher-Student Architecture WACV 2024

Towards Better Structured Pruning Saliency by Reorganizing Convolution WACV 2024

VMFormer: End-to-End Video Matting With Transformer WACV 2024

Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style CVPR 2023

Neighborhood Attention Transformer CVPR 2023

Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning CVPR 2023

Sim2RealVS: A New Benchmark for Video Stabilization With a Strong Baseline WACV 2023

Learning Mask-aware CLIP Representations for Zero-Shot Segmentation NIPS 2023

OneFormer: One Transformer To Rule Universal Image Segmentation CVPR 2023

Graph Transformer GANs for Graph-Constrained House Generation CVPR 2023

Automatic High Resolution Wire Segmentation and Removal CVPR 2023

Keys To Better Image Inpainting: Structure and Texture Go Hand in Hand WACV 2023

Image Completion With Heterogeneously Filtered Spectral Hints WACV 2023

MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices ICCV 2023

Versatile Diffusion: Text, Images and Variations All in One Diffusion Model ICCV 2023

Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators ICCV 2023

More Control for Free! Image Synthesis With Semantic Diffusion Guidance WACV 2023

Boosted Dynamic Neural Networks AAAI 2023

Object Localization Under Single Coarse Point Supervision CVPR 2022

VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution CVPR 2022

AdaFocusV3: On Unified Spatial-Temporal Dynamic Video Recognition ECCV 2022

Point-to-Box Network for Accurate Object Detection via Single Point Supervision ECCV 2022

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image ECCV 2022

DiSparse: Disentangled Sparsification for Multitask Model Compression CVPR 2022

Towards Layer-Wise Image Vectorization CVPR 2022

AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition CVPR 2022

Mask Matching Transformer for Few-Shot Segmentation NIPS 2022

Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search WACV 2022

Adaptive Consistency Regularization for Semi-Supervised Transfer Learning CVPR 2021

Learning to Track Instances without Video Annotations CVPR 2021

Interpretable Visual Reasoning via Induced Symbolic Space ICCV 2021

Any-Precision Deep Neural Networks AAAI 2021

High-Resolution Deep Image Matting AAAI 2021

A Multi-Mode Modulator for Multi-Domain Few-Shot Classification ICCV 2021

CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation AAAI 2021

Rethinking Text Segmentation: A Novel Dataset and a Text-Specific Refinement Approach CVPR 2021