Hogwild! Inference: Parallel LLM Generation via Concurrent Attention Paper • 2504.06261 • Published 12 days ago • 101
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation Paper • 2503.16660 • Published about 1 month ago • 73
Running on Zero 8 8 Unboxing SDXL with SAEs 🚀 Generate and modify images using prompts and features
One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation Paper • 2503.13358 • Published Mar 17 • 96
A Primer on the Inner Workings of Transformer-based Language Models Paper • 2405.00208 • Published Apr 30, 2024 • 10
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers Paper • 2502.15007 • Published Feb 20 • 173
Running 2.48k 2.48k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators Paper • 2502.06394 • Published Feb 10 • 90
CLEAR: Character Unlearning in Textual and Visual Modalities Paper • 2410.18057 • Published Oct 23, 2024 • 210
Mechanistic Permutability: Match Features Across Layers Paper • 2410.07656 • Published Oct 10, 2024 • 19