Yizhuo Li
14 papers · 2020–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Interdisciplinary Bridge π Academic Marathon (5) π Conference Polyglot (6) π Renaissance Researcher (7) πΊοΈ Taxonomy Completionist (40)
π
Interdisciplinary Bridge
π£
Hot Topic Early Bird
πΊοΈ
Taxonomy Completionist
(40)
π§¬
Topic Evolution
ποΈ
Keyword Collector
(71)
π
Century Club
(13)
π₯
Unstoppable
(6)
Conferences
CVPR (4)
ICCV (3)
AAAI (2)
ACL (2)
NIPS (2)
ICLR (1)
Top co-authors
Keywords
video understanding
(4)
object detection
(3)
large language model
(2)
action recognition
(2)
convolutional neural network
(2)
self-supervised learning
(2)
temporal modeling
(1)
video recognition
(1)
semantic segmentation
(1)
video generation
(1)
vision transformer
(1)
video classification
(1)
computer vision
(1)
attention mechanism
(1)
multimodal learning
(1)
in-context learning
(1)
test-time adaptation
(1)
multi-modal learning
(1)
pose estimation
(1)
benchmark evaluation
(1)
Papers
OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Models
ACL 2026
AnRe: Analogical Replay for Temporal Knowledge Graph Forecasting
ACL 2025
Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos
ICCV 2025
Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
CVPR 2025
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
CVPR 2024
InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
ICLR 2024
UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding
ICCV 2023
Unmasked Teacher: Towards Training-Efficient Video Foundation Models
ICCV 2023
Unsupervised Representation for Semantic Segmentation by Implicit Cycle-Attention Contrastive Learning
AAAI 2022
PGT: A Progressive Method for Training Models on Long Videos
CVPR 2021
TDAF: Top-Down Attention Framework for Vision Tasks
AAAI 2021
Test-Time Personalization with a Transformer for Human Pose Estimation
NIPS 2021
HOI Analysis: Integrating and Decomposing Human-Object Interaction
NIPS 2020
TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
CVPR 2020