Kepan Nan
4 papers · 2023–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(11)
Top co-authors
Research topics
Computer Vision
(4)
Deep Learning
(3)
Generation · Computer Vision
(3)
Models
(3)
Machine Learning
(2)
Artificial Intelligence
(1)
Natural Language Processing
(1)
Analysis
(1)
Application Areas
(1)
Architectures
(1)
Core Methods
(1)
Generation · Natural Language Processing
(1)
Learning Paradigms
(1)
Learning Types
(1)
Optimization & Theory
(1)
Keywords
text-to-video generation
(2)
video caption
(2)
video captioning
(1)
multimodal learning
(1)
generative model
(1)
diffusion model
(1)
autoregressive model
(1)
hallucination reduction
(1)
structured caption
(1)
model acceleration
(1)
error accumulation
(1)
temporal correlation
(1)
video diffusion transformer
(1)
few-shot video object segmentation
(1)
instance detection
(1)
memory prototype
(1)
clip prototype
(1)
category discriminability
(1)
prototype learning
(1)
caching mechanism
(1)
Papers
Accelerating Autoregressive Video Diffusion via History-Guided Cache and Residual Correction
CVPR 2026
InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption
CVPR 2025
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
ICLR 2025
Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation
ICCV 2023