Tag
Ember-1 is a specialized AI model from Fireworks Research that achieves Kimi K3's quality with 40% fewer tokens by optimizing reasoning efficiency, aimed at reducing costs in coding and agentic workloads.
GrowPage is an on-demand KV budgeting framework that dynamically manages cache capacity to enhance the efficiency of LLM reasoning serving, achieving a superior performance-throughput trade-off over existing methods.
ParaTempo is a training-free asynchronous parallel reasoning framework that uses temporal confidence to dynamically manage reasoning branches, reducing latency and token usage while maintaining accuracy in mathematical and scientific reasoning benchmarks.
Introduces Thoughts-as-Planning, a framework that models chain-of-thought optimization as sequential decision-making using latent world models and reinforcement learning, outperforming existing methods in efficiency and generalization.