RightNow Research Lab
Habilitando o codesign de modelo e hardware em escala

Membro do NVIDIA Inception, 8 papers no arXiv

Apoio
Director of Accelerated Computing, NVIDIA
Pesquisa

2607.20792cs.LG
Memoir: Should a Model Write to Its Memory While It Thinks?


2606.09682cs.LG
AutoMegaKernel: A Statically-Checked Agent Harness for Self-Retargeting Megakernel Synthesis
Jaber Jaber*, Osama Jaber, 2026

2604.02051cs.LG
Ouroboros: Dynamic Weight Generation for Recursive Transformers via Input-Conditioned LoRA Modulation
Jaber Jaber*, Osama Jaber, 2026

2603.29090cs.LG
HCLSM: Hierarchical Causal Latent State Machines for Object-Centric World Modeling
Jaber Jaber*, Osama Jaber, 2026

2603.21365cs.LG
TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference
Jaber Jaber*, Osama Jaber, 2026
Código aberto
Agent OS
OpenFang
Low-level agent execution with direct OS and GPU access.
RightNow-AI/openfangAbrir repositório
OpenFang: Stars do GitHub
18,209
Contagem da API do GitHub; gráfico ilustrativo
Edge inference
PicoLM
Small inference runtime for memory-constrained edge devices.
RightNow-AI/picolmAbrir repositório
PicoLM: Stars do GitHub
2,193
Contagem da API do GitHub; gráfico ilustrativo
Kernel search
AutoKernel
Profiles PyTorch models, tests Triton variants, and follows measured bottlenecks.
RightNow-AI/autokernelAbrir repositório
AutoKernel: Stars do GitHub
1,564
Contagem da API do GitHub; gráfico ilustrativo



