Reading List: Week of October 18, 2025
Here are 7 papers I find interesting this week. The goal is to read 1-2 per day! π€
-
Failure Prediction at Runtime for Generative Robot Policies
by Ralf RΓΆmer, Adrian Kobras, Luca Worbis, Angela P. Schoellig
Imitation learning (IL) with generative models, such as diffusion and flow matching, has enabled robots to perform complex, long-horizon tasks. Howeve...
-
Weight Weaving: Parameter Pooling for Data-Free Model Merging
by Levy Chaves, Eduardo Valle, Sandra Avila
Model merging provides a cost-effective and data-efficient combination of specialized deep neural networks through parameter integration. This techniq...
-
Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
by Cong Zeng, Shengkun Tang, Yuanzhou Chen, Zhiqiang Shen, Wenchao Yu, Xujiang Zhao, Haifeng Chen, Wei Cheng, Zhiqiang Xu
The rapid advancement of large language models (LLMs) such as ChatGPT, DeepSeek, and Claude has significantly increased the presence of AI-generated t...
-
Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
by Yue Hou, He Zhu, Ruomei Liu, Yingke Su, Junran Wu, Ke Xu
Distributional discrepancy between training and test data can lead models to make inaccurate predictions when encountering out-of-distribution (OOD) s...
-
Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry
by Atharv Goel, Sharat Agarwal, Saket Anand, Chetan Arora
Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy o...
-
Exploring and Leveraging Class Vectors for Classifier Editing
by Jaeik Kim, Jaeyoung Do
Image classifiers play a critical role in detecting diseases in medical imaging and identifying anomalies in manufacturing processes. However, their p...
-
Test-Time Adaptation by Causal Trimming
by Yingnan Liu, Rui Qiao, Mong Li Lee, Wynne Hsu
Test-time adaptation aims to improve model robustness under distribution shifts by adapting models with access to unlabeled target samples. A primary ...