Meta FAIR's AI Research Preference Models rank unexecuted ML candidates, raising AIRS-Bench from 0.684 to 0.729 without ...
Google releases TimesFM-3, a 330M parameter zero-shot foundation model for multivariate time series forecasting in one ...
Keenable AI open-sources NEEDLE, a live benchmark that rebuilds search queries hourly and scores 15 APIs for agents.
Benchmarking the lowest-latency inference APIs for voice agents: measured TTFT, time to first audio, and full-pipeline ...
Google introduces EnvHarness, a programmable layer that reshapes static LLM agent environments without modifying their code.
Princeton, Ant Group and Stanford built AQuA, two self-improving quant research agents whose sealed sandbox makes data leakage unwritable ...
Today, Meta has introduced Muse, a personal AI agent that takes actions rather than just answering questions. Muse can send emails, book travel, negotiate ...
The six models share a core architecture, vocabulary, training methodology, interfaces and deployment tooling. The 0.9B model uses a smaller vocabulary. That consistency is the point: teams can ...
Today, Meta has introduced Muse, a personal AI agent that takes actions rather than just answering questions. Muse can send emails, book travel, negotiate ...
Most visual document retrievers in production today are hand-me-downs. ColPali and the models that followed it take a generative vision-language model and repurpose it as an encoder. The result still ...
Multi-agent workflows have changed the shape of local inference. A lead agent decomposes a task and spawns subagents. What looked like one user request becomes dozens of independent model calls.
Results that may be inaccessible to you are currently showing.
Hide inaccessible results