Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations
Video diffusion transformers (vDiTs) generate high quality video but introduce extremely high compute cost due to the long diffusion timesteps and self attention computation. As diffusion timesteps are reduced, the computation cost of self attention becomes the dominant bottleneck. Existing acceleration approaches largely inherit sparse attention techniques from large language models, which fail to consider the unique spatiotemporal correlation of video data. This paper presents Kaleido, an algorithm hardware codesign that accelerates all operations in vDiTs by exploiting channel-wise spatio
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-xl-base-1.0 →
“Fuzzy title match (0.73): “Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Tr” ≈ “stabilityai/stable-diffusion-xl-base-1.0””
- FuzzySimilar title/name (fuzzy) · 59%CompVis/stable-diffusion-v1-4 →
“Fuzzy title match (0.73): “Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Tr” ≈ “CompVis/stable-diffusion-v1-4””
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-3.5-large →
“Fuzzy title match (0.73): “Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Tr” ≈ “stabilityai/stable-diffusion-3.5-large””
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-video-diffusion-img2vid-xt →
“Fuzzy title match (0.73): “Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Tr” ≈ “stabilityai/stable-video-diffusion-img2vid-xt””
- PossiblePossibly related (embedding) · 46%DiffusionGemma: 4x faster text generation →
- FuzzySimilar title/name (fuzzy) · 87%lucidrains/x-transformers →
“Fuzzy title match (0.94): “Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Tr” ≈ “lucidrains/x-transformers””
- FuzzySimilar title/name (fuzzy) · 84%huggingface/transformers →
“Fuzzy title match (0.92): “Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Tr” ≈ “huggingface/transformers””
- FuzzyOverlapping authors or contributors · 62%langchain-ai/langchain →
“Shared author/contributor keys: gan”