Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? Paper • 2602.14111 • Published Feb 15 • 56
SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens Paper • 2508.05305 • Published Aug 7, 2025 • 49
T-LoRA: Single Image Diffusion Model Customization Without Overfitting Paper • 2507.05964 • Published Jul 8, 2025 • 121