modular-ai

Tag

Cards List
#modular-ai

@Modular: People ask what our secret is when they see our performance numbers. Brendan Hansknecht, AI Performance Engineering Man…

X AI KOLs Timeline · 4d ago Cached

Brendan Hansknecht from Modular explains that their high performance numbers stem from treating performance as a full-stack problem, rather than relying on piecemeal components in production.

0 favorites 0 likes
#modular-ai

@GVteam: Congrats to @clattner_llvm @iamtimdavis and the @Modular team on #ModCon2026. Event takeaways from @davemuni below:

X AI KOLs Following · 2026-08-20 Cached

ModCon2026, a developer conference by Modular, focused on discussions about AI infrastructure, the economics of training and inference, and the impact of open models, with takeaways highlighted by Dave Munichiello.

0 favorites 0 likes
#modular-ai

Scaling Participation in Modular AI Systems

arXiv cs.AI · 2026-06-09 Cached

This paper introduces scaling participation, a new paradigm for building modular AI systems through contributions from diverse stakeholders, where small models collaborate to outperform monolithic LLMs by up to 15.4% across various tasks, demonstrating emergent capabilities and improved diversity benefits.

0 favorites 0 likes
#modular-ai

Cartridges at Scale: Training Modular KV Caches over Large Document Collections

arXiv cs.CL · 2026-06-04 Cached

Researchers from Amazon AGI introduce Cartridges at Scale (CAS), a training framework that distills document collections into modular, reusable KV caches, enabling scalable multi-cartridge learning over collections exceeding one million tokens. CAS improves over monolithic cartridge baselines by 10–31 points and matches or exceeds conventional RAG accuracy while consuming 3–4× fewer prompt tokens.

0 favorites 0 likes
#modular-ai

PDRNN: Modular Data-driven Pedestrian Dead Reckoning on Loosely Coupled Radio- and Inertial-Signalstreams

arXiv cs.LG · 2026-05-18 Cached

Proposes PDRNN, a modular hybrid AI-assisted pedestrian dead reckoning system that combines a recurrent neural network with separate ML models for orientation, velocity, and distance estimation, with optional radio-based stabilization. Experiments on dynamic sports movement data show superior accuracy and precision compared to classic and ML-based methods.

0 favorites 0 likes
← Back to home

Submit Feedback