Structure-Preserving Network Compression Via Low-Rank Induced Training Through Linear Layers Compositionby Xitong Zhang, Ismail R.…
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Modelsby George-Octavian Barbulescu,…
Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMsby Jordan Dotzel,…
TK-Planes: Tiered K-Planes with High Dimensional Feature Vectors for Dynamic UAV-based Scenesby Christopher Maxey, Jaehoon…
Sub-goal Distillation: A Method to Improve Small Language Agentsby Maryam Hashemzadeh, Elias Stengel-Eskin, Sarath Chandar,…
Beyond Unimodal Learning: The Importance of Integrating Multiple Modalities for Lifelong Learningby Fahad Sarfraz, Bahram…
Assessing Adversarial Robustness of Large Language Models: An Empirical Studyby Zeyu Yang, Zhao Meng, Xiaochen…
Linear Convergence of Independent Natural Policy Gradient in Games with Entropy Regularizationby Youbang Sun, Tao…
PhilHumans: Benchmarking Machine Learning for Personal Healthby Vadim Liventsev, Vivek Kumar, Allmin Pradhap Singh Susaiyah,…
MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learningby Vishal Nedungadi, Ankit Kariryaa, Stefan Oehmcke,…