Sebastian Dziadzio

5 papers · 2021–2025 · 4 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 · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird ❓ The Questioner

Venues

ICCV (2) ACL (1) CVPR (1) NeurIPS (1)

Top co-authors

Vishaal Udandarao (3) Matthias Bethge (3) Ameya Prabhu (3) Samuel Albanie (3) Jamie Shotton (2) Karsten Roth (2) Thomas J. Cashman (2) Zeynep Akata (2) Erroll Wood (1) Tadas Baltrusaitis (1)

Research topics

Machine Learning (4) Application Areas (3) Artificial Intelligence (2) Computer Vision (2) Deep Learning (2) Analysis (2) Learning Types (2) Core AI (1) Learning Paradigms (1) Models (1) Optimization & Theory (1) Processing (1) Techniques (1)

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 data (1) continual pre-training (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

How to Merge Your Multimodal Models Over Time? CVPR 2025 ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities ACL 2025 A Practitioner's Guide to Real-World Continual Multimodal Pretraining NeurIPS 2024 Fake It Till You Make It: Face Analysis in the Wild Using Synthetic Data Alone ICCV 2021 Full-Body Motion From a Single Head-Mounted Device: Generating SMPL Poses From Partial Observations ICCV 2021