Shufan Li
9 papers · 2023–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (7) π Cross-Pollinator (7) πΊοΈ Taxonomy Completionist (17)
π£
Hot Topic Early Bird
Conferences
ICCV (2)
NIPS (2)
CVPR (1)
ECCV (1)
ICLR (1)
ICML (1)
NAACL (1)
Top co-authors
Keywords
text-to-image generation
(2)
vision transformer
(1)
image editing
(1)
instruction following
(1)
remote sensing
(1)
model alignment
(1)
hierarchical representation
(1)
diffusion model
(1)
open-vocabulary segmentation
(1)
reference image
(1)
model fine-tuning
(1)
human preference alignment
(1)
masked autoencoder
(1)
bandpass filter
(1)
rectified flow
(1)
panoptic segmentation
(1)
human preference
(1)
diffusion model alignment
(1)
utility maximization
(1)
binary feedback
(1)
Papers
OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
CVPR 2025
Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection
ICCV 2025
SegLLM: Multi-round Reasoning Segmentation with Large Language Models
ICLR 2025
InstructAny2Pix: Image Editing with Multi-Modal Prompts
NAACL 2025
Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data
ECCV 2024
xT: Nested Tokenization for Larger Context in Large Images
ICML 2024
Aligning Diffusion Models by Optimizing Human Utility
NIPS 2024
Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning
ICCV 2023
Hierarchical Open-vocabulary Universal Image Segmentation
NIPS 2023