Tomasz Trzcinski

LumiMotion: Improving Gaussian Relighting with Scene Dynamics CVPR 2026 Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers WACV 2025 Exploring the Stability Gap in Continual Learning: The Role of the Classification Head WACV 2025 GEPAR3D: Geometry Prior-Assisted Learning for 3D Tooth Segmentation MICCAI 2025 How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies ICML 2025 Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers ICML 2025 LumiGauss: Relightable Gaussian Splatting in the Wild WACV 2025 RegScore: Scoring Systems for Regression Tasks MICCAI 2025 AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale ECCV 2024 Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-Free Continual Learning WACV 2024 Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery ECCV 2024 CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation ECCV 2024 CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free WACV 2024 Divide and not forget: Ensemble of selectively trained experts in Continual Learning ICLR 2024 HyperCube: Implicit Field Representations of Voxelized 3D Models (Student Abstract) AAAI 2024 Let Me DeCode You: Decoder Conditioning with Tabular Data MICCAI 2024 MagMax: Leveraging Model Merging for Seamless Continual Learning ECCV 2024 Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning ICML 2024 Revisiting Supervision for Continual Representation Learning ECCV 2024 TabMixer: Noninvasive Estimation of the Mean Pulmonary Artery Pressure via Imaging and Tabular Data Mixing MICCAI 2024 Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning NeurIPS 2024 Towards More Realistic Membership Inference Attacks on Large Diffusion Models WACV 2024 Active Visual Exploration Based on Attention-Map Entropy IJCAI 2023 BlendFields: Few-Shot Example-Driven Facial Modeling CVPR 2023 Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders NeurIPS 2023 The Tunnel Effect: Building Data Representations in Deep Neural Networks NeurIPS 2023 CoNeRF: Controllable Neural Radiance Fields CVPR 2022 Continual Learning with Guarantees via Weight Interval Constraints ICML 2022 FlowHMM: Flow-based continuous hidden Markov models NeurIPS 2022 Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning IJCAI 2022 On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models NeurIPS 2022 Explaining Self-Supervised Image Representations with Visual Probing IJCAI 2021 Non-Gaussian Gaussian Processes for Few-Shot Regression NeurIPS 2021 Zero Time Waste: Recycling Predictions in Early Exit Neural Networks NeurIPS 2021 Hypernetwork approach to generating point clouds ICML 2020 Plugin Networks for Inference under Partial Evidence WACV 2020 BinGAN: Learning Compact Binary Descriptors with a Regularized GAN NeurIPS 2018 Boosting Binary Keypoint Descriptors CVPR 2013 Learning Image Descriptors with the Boosting-Trick NeurIPS 2012