We have 4 of 48 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Self-evolving agents are usually scored by endpoint Gain: held-out success after an update minus success before. That difference can credit a frozen rescore as evolution. We introduce Trace Evolution Bench (TEB), a protocol that separates that rescore from a context or weight update, together with three frozen 80/20/40...
Large language models (LLMs) are increasingly used for everyday assistance, yet existing benchmarks only partially reflect the requests users naturally make in practice. Real-world requests are often open-ended, casually specified, and context-dependent, requiring models not only to follow explicit instructions but als...
ZenGen, an integrated framework for measuring, internalizing, and grounding social intelligence, and Actio, a harness-controlled inference architecture that routes four typed supports into reasoning demonstrate the effectiveness of typed runtime support.
This work presents Meta's network architecture and software stack designed to support one of the world's largest RoCE fabrics, currently connecting over 100,000 GPUs across multiple datacenter buildings, and introduces a scalable initialization strategy that reduces startup times by 11× via eager process group creation...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
