New ‘Test-Time Training’ method lets AI keep learning without exploding inference costs

By allowing models to actively update their weights during inference, Test-Time Training (TTT) creates a "compressed memory" that solves the latency bottleneck of long-document analysis.
InfoQ

OpenAI Presents Research on Inference-Time Compute to Better AI Security

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...
VentureBeat

Inference framework Archon promises to make LLMs quicker, without additional costs

Join the event trusted by enterprise leaders for nearly two decades. VB Transform brings together the people building real enterprise AI strategy. Learn more Researchers from Stanford University‘s ...
NextBigFuture

Cogito v2 – Inference-time search and New AI Self-improvement

The largest Cogito v2 671B MoE model is amongst the strongest open models in the world. It matches/exceeds the performance of the latest DeepSeek v3 and DeepSeek R1 models both, and approaches closed ...
Seeking Alpha

NTT Announces AI Inference Chip for Real-Time 4K Video Processing

NTT unveils AI inference LSI that enables real-time AI inference processing from ultra-high-definition video on edge devices and terminals with strict power constraints. Utilizes NTT-created AI ...