CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training Paper • 2504.13161 • Published 9 days ago • 87
mechanistic interpretability with sparse autoencoders Collection A collection of papers that I found useful for learning about using Sparse Autoencoders for finding interpretable features in language models • 9 items • Updated Sep 3, 2024 • 2
UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving Paper • 2503.24381 • Published 26 days ago • 1
Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization Paper • 2502.13146 • Published Feb 18 • 1