Sören Pirk
12 papers · 2021–2026 · 8 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (26)
💎
Century Club · Bronze
🌈
Renaissance Researcher
(6)
🗃️
Keyword Collector
(65)
Top co-authors
Research topics
Deep Learning
(6)
Artificial Intelligence
(5)
Computer Vision
(5)
Machine Learning
(4)
Analysis
(4)
Core AI
(4)
Core Methods
(3)
Models
(3)
Reinforcement Learning
(2)
Architectures
(2)
Generation
(2)
Learning Types · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Methods
(2)
Computer Science
(1)
Keywords
3d reconstruction
(3)
depth estimation
(2)
semantic segmentation
(2)
neural radiance field
(2)
generative model
(2)
self-supervised learning
(1)
multi-task learning
(1)
reinforcement learning
(1)
visual navigation
(1)
synthetic data
(1)
procedural generation
(1)
continuous optimization
(1)
early exit
(1)
survival analysis
(1)
image synthesis
(1)
diffusion model
(1)
real-time simulation
(1)
image clustering
(1)
attention mechanism
(1)
vision transformer
(1)
Papers
ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
AAAI 2026
Attention-to-Survival: Multimodal Fracture Risk Prediction Based on Pelvic Radiographs and Clinical Data from the Study of Osteoporotic Fractures
MIDL 2026
ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference
CVPR 2026
Augmented Mass-Spring Model for Real-Time Dense Hair Simulation
ICCV 2025
Perm: A Parametric Representation for Multi-Style 3D Hair Modeling
ICLR 2025
Real Super-Resolution for Proximal Femur: Enhanced Computation of Structural Bone Metrics from Clinical CTs
MICCAI 2025
Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
CVPR 2024
Consistent Multimodal Generation via a Unified GAN Framework
WACV 2024
LRM-Zero: Training Large Reconstruction Models with Synthesized Data
NeurIPS 2024
3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets
ICCV 2023
GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning
ICCV 2023
Taskology: Utilizing Task Relations at Scale
CVPR 2021