kimodo.cpp is live. NVIDIA's Kimodo, the best AI animation model right now, running natively on CPU or Vulkan.
Type a sentence, get character animation, locally on your own machine.
Before, you needed the whole PyTorch and CUDA stack standing up before you could generate a single motion. Now it is a native C++/GGML build that loads GGUF models and comes with a local web demo. No Python environment to fight.
It gives you SMPL-X, and from there you retarget onto pretty much any skeleton you want, like Mixamo.
Great piece of work @jichiep
Proud to share our lab’s @MMLabNTU work Log-linear Sparse Attention (LLSA) - a trainable sparse attention mechanism that reduces attention complexity from O(N²) to O(N log N), making diffusion transformers much more efficient.
Also, special shout-out to the first author @zhouyifan1107 for presenting the poster in full costume - truly above and beyond. The level of dedication is impressive! 👏
#CVPR2026 #DiffusionModels #EfficientAI #SparseAttention
instead of watching 2 hours of Netflix tonight, watch this 40-minute masterclass from the founder of a $20B China AI company
it's the clearest explanation I've seen of how Agent Swarms and AI systems actually work at scale
useful whether you've never built an agent in your life or have been using Claude every day for the past year
I took the key ideas and turned them into a practical guide on how to actually build with Kimi
find it below
RL is no longer needed?
"Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights"
This paper argues that large pretrained models don’t sit at a single optimal set of weights but inside a dense “thicket” of nearby task-specific experts.
So once pretraining is strong enough, randomly sampling small weight perturbations often yields specialists that outperform the base model on different tasks, and simply selecting and ensembling these guesses (RandOpt) can rival standard post-training methods.
This suggests that much of what post-training does is just selecting useful behaviors already latent around the pretrained weights rather than learning entirely new ones.