view article Article Did GPT 5.2 make a breakthrough discovery in theoretical physics? 13 days ago • 59
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 13 days ago • 475
When Models Manipulate Manifolds: The Geometry of a Counting Task Paper • 2601.04480 • Published Jan 8 • 4
view article Article From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output 25 days ago • 21
view article Article Training Design for Text-to-Image Models: Lessons from Ablations 29 days ago • 66
Understanding self-supervised Learning Dynamics without Contrastive Pairs Paper • 2102.06810 • Published Feb 12, 2021 • 1
view article Article Introducing Daggr: Chain apps programmatically, inspect visually +3 Jan 29 • 103
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think Paper • 2410.06940 • Published Oct 9, 2024 • 12
view article Article Tokenization in Transformers v5: Simpler, Clearer, and More Modular +4 Dec 18, 2025 • 120
view article Article Qwen-Image-i2L: Training Strategies for Image-to-LoRA Generation Dec 16, 2025 • 56