I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders Paper • 2503.18878 • Published 1 day ago • 82
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation Paper • 2503.16660 • Published 5 days ago • 62
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity Paper • 2502.13063 • Published Feb 18 • 67
Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation Paper • 2412.06531 • Published Dec 9, 2024 • 71
nGPT: Normalized Transformer with Representation Learning on the Hypersphere Paper • 2410.01131 • Published Oct 1, 2024 • 10