Here are seven papers I find interesting this week. The goal is to read one or two per day. The list refreshes each week — check back for the latest pile of arXiv tabs I haven't quite closed yet. 🤓
Week of
Paper 1 of 7
Failure Prediction at Runtime for Generative Robot Policies
Imitation learning (IL) with generative models, such as diffusion and flow matching, has enabled robots to perform complex, long-horizon tasks. Howeve...
Paper 2 of 7
Weight Weaving: Parameter Pooling for Data-Free Model Merging
Model merging provides a cost-effective and data-efficient combination of specialized deep neural networks through parameter integration. This techniq...
Paper 3 of 7
Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
The rapid advancement of large language models (LLMs) such as ChatGPT, DeepSeek, and Claude has significantly increased the presence of AI-generated t...
Paper 4 of 7
Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
Distributional discrepancy between training and test data can lead models to make inaccurate predictions when encountering out-of-distribution (OOD) s...
Paper 5 of 7
Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry
Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy o...
Paper 6 of 7
Exploring and Leveraging Class Vectors for Classifier Editing
Image classifiers play a critical role in detecting diseases in medical imaging and identifying anomalies in manufacturing processes. However, their p...
Paper 7 of 7
Test-Time Adaptation by Causal Trimming
Test-time adaptation aims to improve model robustness under distribution shifts by adapting models with access to unlabeled target samples. A primary ...