Finally, they added a wide diffusion head the DiTDH variant. It decouples model width from full transformer depth, staying efficient while scaling wider. Result: 2.16 FID on ImageNet-256. RAE-DiTDH outperforms every VAE-based diffusion model at every scale.
INNOVATION
-

Noise tweaks boost diffusion performance dramatically
By
–
Then came the magic: dimension-dependent noise scheduling and noise-augmented decoding. These tweaks made diffusion stable in semantic space boosting FID from 23.08 → 4.28. RAE models now converge 47× faster than SiT or REPA.
-

DiT Convergence: Width Over Depth Matters
By
–
Diffusion Transformers struggled at first. Why? Their width was too small for RAE’s high-dimensional latents. The fix: scale width ≥ latent dimension. Once model width ≥ 768, DiT started converging instantly. Depth didn’t matter width unlocked training stability.
-

RAE + DINOv2-B beats VAEs with sharper images
By
–
Everyone assumed semantic encoders couldn’t reconstruct images.
Turns out, they can and better than VAEs. RAE + DINOv2-B achieves 0.49 rFID vs 0.62 for SD-VAE, with 6× less compute. That’s fewer FLOPs and sharper reconstructions. -

RAEs improve diffusion models over VAEs
By
–
Today, most diffusion models still use VAEs built on 2021 tech. They compress images into low-dimensional latents (like 4 channels). That’s why diffusion models lose global structure and texture fidelity. RAEs fix this by encoding rich semantic features directly from pretrained
-

New Paper Revolutionizes Diffusion Models
By
–
Holy shit…Diffusion just leveled up A new paper “Diffusion Transformers with Representation Autoencoders” basically kills the VAE era. Instead of the old VAE bottleneck, they use representation autoencoders (RAEs) built from pretrained encoders like DINO or SigLIP. The
-

AGI Jobs Platform Launches Meta-Agents and Alpha-AGI Governance
By
–
[ AGI Jobs v0 — the OS for AGI Work ] ASI Takes Off Meta‑Agents • α‑AGI Governance • Chainless UX • RSI↑ https://
github.com/MontrealAI/AGI
Jobsv0
… | https://
agialpha.com $AGIALPHA #AGIALPHA #ASIFirst -

Open datasets trend enables independent model training
By
–
I love the diversity of trending open datasets these days. There’s no excuse anymore not to train your own models! – Fineweb and a shuffle of it by @karpathy – Webscale-RL, a large-scale reinforcement learning dataset from @salesforce – SVQ, an audio dataset from @Google –
-
Small Manufacturers Leverage Real-Time Data IoT Solutions
By
–
“Small manufacturers can’t afford to wait.”
— Lucian Fogoros (@fogoros) 18 octobre 2025
Peggy Gulick’s advice for every shop floor leader:
• Get your arms around your data.
• Deliver real-time answers.
• Compete with the speed of Amazon-like service.
🎥 Watch her take: https://t.co/HksMEdPnmE #intelliShift_iiot pic.twitter.com/zrtYH5O2yZ“Small manufacturers can’t afford to wait.”
Peggy Gulick’s advice for every shop floor leader:
• Get your arms around your data.
• Deliver real-time answers.
• Compete with the speed of Amazon-like service. Watch her take: https://
buff.ly/tWyHBPU #intelliShift_iiot -
Top 5 Technology Trends Reshaping 2026 Innovation
By
–
The Top 5 Technology Trends for 2026 From intelligent agents and space computing to bio-tech and digital twins, these are the five technological shifts set to reshape business, society and innovation in 2026. Read more https://
bernardmarr.com/the-top-5-tech
nology-trends-for-2026/
… #TechTrends #Innovation
