• GROOD - GRadient-aware Out-Of-Distribution detection

  Publications  · 12 Sep 2025 - 10 minutes to read.

  Download the paper Check the code

  Out-of-Distribution (OOD) detection, the task of identifying inputs that a model has not been trained on, is fundamental for the safe and reliable deployment of deep learning models in real-world applications like autonomous driving and healthcare. Models that perform well on familiar, in-distribution...

• Decoding LLM Hallucinations An In-Depth Survey Summary

  Paper Review  · 29 Apr 2025 - 14 minutes to read.

  The rapid advancement of Large Language Models (LLMs) has brought transformative capabilities, yet their tendency to “hallucinate”—generating outputs that are nonsensical, factually incorrect, or unfaithful to provided context—poses significant risks to their reliability, especially in information-critical applications . A comprehensive survey by Huang (Huang et al., 2025) systematically explores this phenomenon, offering a detailed taxonomy, analyzing root causes,...

• Topology of Out-of-Distribution Examples in Deep Neural Networks

  Paper Review  · 21 Apr 2025 - 4 minutes to read.

  Download the paper Check the code 

  As deep neural networks (DNNs) become more common, concerns about their robustness, particularly when facing unfamiliar inputs, are growing. These models often exhibit overconfidence when making incorrect predictions on out-of-distribution (OOD) examples. This...