Zizheng Pan
17 papers · 2020–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (7) π Academic Marathon (5) π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (29)
π
Conference Polyglot
(7)
π
Academic Marathon
(5)
π
Renaissance Researcher
(5)
π€
Dynamic Duo
(12)
π
Century Club
(17)
ποΈ
Keyword Collector
(60)
π₯
Unstoppable
(6)
Conferences
CVPR (5)
ECCV (3)
NIPS (3)
ICCV (2)
ICLR (2)
AAAI (1)
IJCAI (1)
Top co-authors
Keywords
vision transformer
(4)
model compression
(3)
large language model
(3)
transformer architecture
(2)
object detection
(2)
image generation
(2)
model stitching
(2)
multimodal understanding
(2)
autoregressive model
(2)
transfer learning
(2)
vision-language model
(2)
image classification
(2)
efficient computing
(2)
multimodal learning
(2)
knowledge distillation
(1)
attention mechanism
(1)
efficient training
(1)
computational efficiency
(1)
scene understanding
(1)
neural network optimization
(1)
Papers
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
ICLR 2025
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
CVPR 2025
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
CVPR 2025
PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction
ICLR 2025
Efficient Stitchable Task Adaptation
CVPR 2024
Stitched ViTs are Flexible Vision Backbones
ECCV 2024
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
NIPS 2024
A Survey on Efficient Training of Transformers
IJCAI 2023
Dynamic Focus-Aware Positional Queries for Semantic Segmentation
CVPR 2023
Stitchable Neural Networks
CVPR 2023
Less Is More: Pay Less Attention in Vision Transformers
AAAI 2022
Fast Vision Transformers with HiLo Attention
NIPS 2022
EcoFormer: Energy-Saving Attention with Linear Complexity
NIPS 2022
An Efficient Spatio-Temporal Pyramid Transformer for Action Detection
ECCV 2022
Scalable Vision Transformers With Hierarchical Pooling
ICCV 2021
The Road To Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
ICCV 2021
Object-and-Action Aware Model for Visual Language Navigation
ECCV 2020