Zobrazeno 1 - 10
of 106
pro vyhledávání: '"Zieba, Maciej"'
Low-rank adaptation (LoRA) is a fine-tuning technique that can be applied to conditional generative diffusion models. LoRA utilizes a small number of context examples to adapt the model to a specific domain, character, style, or concept. However, due
Externí odkaz:
http://arxiv.org/abs/2410.03941
Autor:
Merta, Łukasz, Zięba, Maciej
In this note we study line and conic arrangements associated to sextactic and type 9 points on the Fermat cubic $F$ and we provide explicit coordinates for each of the 72 type 9 points on $F$.
Comment: 9 pages
Comment: 9 pages
Externí odkaz:
http://arxiv.org/abs/2406.13802
Unifying Perspectives: Plausible Counterfactual Explanations on Global, Group-wise, and Local Levels
Growing regulatory and societal pressures demand increased transparency in AI, particularly in understanding the decisions made by complex machine learning models. Counterfactual Explanations (CFs) have emerged as a promising technique within Explain
Externí odkaz:
http://arxiv.org/abs/2405.17642
We present PPCEF, a novel method for generating probabilistically plausible counterfactual explanations (CFs). PPCEF advances beyond existing methods by combining a probabilistic formulation that leverages the data distribution with the optimization
Externí odkaz:
http://arxiv.org/abs/2405.17640
Autor:
Miłkowski, Piotr, Karanowski, Konrad, Wielopolski, Patryk, Kocoń, Jan, Kazienko, Przemysław, Zięba, Maciej
Designing predictive models for subjective problems in natural language processing (NLP) remains challenging. This is mainly due to its non-deterministic nature and different perceptions of the content by different humans. It may be solved by Persona
Externí odkaz:
http://arxiv.org/abs/2312.06034
Enhancing low-light images while maintaining natural colors is a challenging problem due to camera processing variations and limited access to photos with ground-truth lighting conditions. The latter is a crucial factor for supervised methods that ac
Externí odkaz:
http://arxiv.org/abs/2310.09633
State-of-the-art models can perform well in controlled environments, but they often struggle when presented with out-of-distribution (OOD) examples, making OOD detection a critical component of NLP systems. In this paper, we focus on highlighting the
Externí odkaz:
http://arxiv.org/abs/2307.07002
Self-supervised methods have been proven effective for learning deep representations of 3D point cloud data. Although recent methods in this domain often rely on random masking of inputs, the results of this approach can be improved. We introduce Poi
Externí odkaz:
http://arxiv.org/abs/2307.05325
NeRF is a popular model that efficiently represents 3D objects from 2D images. However, vanilla NeRF has a few important limitations. NeRF must be trained on each object separately. The training time is long since we encode the object's shape and col
Externí odkaz:
http://arxiv.org/abs/2305.10579