SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published 7 days ago • 64
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper • 2502.05171 • Published Feb 7 • 124
Running 535 535 Scaling test-time compute 📈 Enhance math problem solving by scaling test-time compute
SNOOPI: Supercharged One-step Diffusion Distillation with Proper Guidance Paper • 2412.02687 • Published Dec 3, 2024 • 109
TinyFusion: Diffusion Transformers Learned Shallow Paper • 2412.01199 • Published Dec 2, 2024 • 14
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training Paper • 2411.13476 • Published Nov 20, 2024 • 16
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders Paper • 2410.22366 • Published Oct 28, 2024 • 78
Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss Paper • 2410.17243 • Published Oct 22, 2024 • 92
Addition is All You Need for Energy-efficient Language Models Paper • 2410.00907 • Published Oct 1, 2024 • 148
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality Paper • 2405.21060 • Published May 31, 2024 • 67