What a weekend. Around 30 teams showed up to build on Laguna XS.2, and the bar was very, very high.
Winners below 🏆
1st: Overthinking Machines Labs
@emilfristed
Pseudo-full-duplex with text-only models through dialogue modeling with silence tokens.
https://huggingface.co/spaces/poolside-laguna-hackathon/poor-mans-interaction-models
2nd: Coding Kernels by the Pool
Charlie Masters, Evan O’Leary, Jessica Mak
Laguna-Dense: a ~3B fully dense distillation of Laguna XS.2 for generating CUDA kernels from PyTorch.
https://huggingface.co/EvanOLeary/laguna-xs2-dense-k8-cuda-dpo
3rd: attnvq
@alaradirik
Attention-aware product vector quantization of KV caches.
https://huggingface.co/spaces/adirik/attnvq
Honorary mention: Laguna Vision
Aaron Kazah @aaronkazah
A SigLIP vision encoder + resampler + LoRA adapters, trained on 300k examples to give Laguna XS.2 a native visual input path.
https://huggingface.co/poolside-laguna-hackathon/laguna-vision
Huge congrats to the winners, and thank you to everyone who hacked, demoed, judged, helped, and pushed Laguna XS.2 in directions we would not have found on our own!
@nvidia @PrimeIntellect @adaption_ai @huggingface