Sebastian Dziadzio
5 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (12) π Conference Polyglot (4) π Interdisciplinary Bridge π Cross-Pollinator (15) π§ Keyword Pioneer
π£
Hot Topic Early Bird
β
The Questioner
Conferences
ICCV (2)
ACL (1)
CVPR (1)
NIPS (1)
Top co-authors
Keywords
foundation model
(3)
multimodal learning
(2)
domain adaptation
(1)
parameter estimation
(1)
face analysis
(1)
human pose estimation
(1)
model merging
(1)
motion generation
(1)
variational autoencoder
(1)
synthetic datum
(1)
continual pretraining
(1)
pose forecasting
(1)
full-body motion estimation
(1)
smpl pose
(1)
human skeleton
(1)
pose prediction
(1)
landmark localization
(1)
face parsing
(1)
aggregation algorithm
(1)
temporal model merging
(1)
Papers
ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities
ACL 2025
How to Merge Your Multimodal Models Over Time?
CVPR 2025
A Practitioner's Guide to Real-World Continual Multimodal Pretraining
NIPS 2024
Full-Body Motion From a Single Head-Mounted Device: Generating SMPL Poses From Partial Observations
ICCV 2021
Fake It Till You Make It: Face Analysis in the Wild Using Synthetic Data Alone
ICCV 2021