A sparse set of massive activation channels in DiTs carries semantic information, proven critical by disruption tests, spatially aligned with image subjects via clustering, and transferable for semantic interpolation between prompts.
Attention is all you need
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
FairyFuse enables multiplication-free ternary LLM inference on CPUs via fused AVX-512 kernels, achieving 29.6x kernel speedup and 32.4 tokens/s on Xeon with near-lossless quality.
citing papers explorer
-
Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
A sparse set of massive activation channels in DiTs carries semantic information, proven critical by disruption tests, spatially aligned with image subjects via clustering, and transferable for semantic interpolation between prompts.
-
FairyFuse: Multiplication-Free LLM Inference on CPUs via Fused Ternary Kernels
FairyFuse enables multiplication-free ternary LLM inference on CPUs via fused AVX-512 kernels, achieving 29.6x kernel speedup and 32.4 tokens/s on Xeon with near-lossless quality.
- GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction