view article Article How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications Dharma-AI • 22 days ago • 38
NONHUMAN-RESEARCH/hanoi-triple-disk-in-tower-reset UR5 • Updated 24 days ago • 300 episodes • 204 • 1
view article Article Hugging Face ❤️ TorchTPU: TPUs, Natively +3 tengomucho, Jingya, pagezyhf, jeffboudier, regisss • 24 days ago • 56
view article Article Open-sourcing AstaBrief, the fast report-generation model in Asta allenai • Oct 2 • 28
view article Article Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem MultiverseComputingCAI • Sep 21 • 34
view article Article Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps +1 iamleonie, burtenshaw, sergiopaniego • Sep 3 • 162
view article Article NeoMME: an efficient Multimodal-native and Multilingual Encoder Hcompany • Sep 3 • 122
view article Article Real-Time Intelligence with IBM Time Series Models on Confluent ibm-research • Sep 2 • 53