5 papers
DART: A Degradation-Aware Recurrent Transformer for Archival Film Restoration
MikoÅaj JastrzÄbski, Wojciech KozÅowski, Kamil Adamczewski
Archival film restoration is a challenging problem because historical footage contains compound degradations such as scratches, dust, blur, noise, flicker, and photometric aging, w…
AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark
MikoÅaj JastrzÄbski, Dawid Glinkowski, Dawid ZieliÅski +3
Restoring archival film remains a fundamentally challenging problem due to the absence of paired training data and the lack of standardized evaluation benchmarks. Pristine versions…
One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
MikoÅaj Janusz, Tomasz Wojnar, Yawei Li +2
Pruning is a core technique for compressing neural networks to improve computational efficiency. This process is typically approached in two ways: one-shot pruning, which involves…
Unifying Deep Stochastic Processes for Image Enhancement
Wojciech KozÅowski, Wojciech Kozłowski, RadosÅaw KuczbaÅski +5
Deep stochastic processes have recently become a central paradigm for image enhancement, with many methods explicitly conditioning the stochastic trajectory on the degraded input.…
Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models
Jakub Binkowski, Kamil Adamczewski, Tomasz Kajdanowicz
Large language models frequently exhibit hallucinations: fluent and confident outputs that are factually incorrect or unsupported by the input context. While recent hallucination d…