When we say that a robot uses memory, does that memory actually play a role? Success-rate ablations alone cannot establish the use of task-relevant facts: they change information and computation together, while aggregate rates can hide offsetting gains and losses. We propose an Interventional Memory Evaluation Protocol...
Ke-Yuan Luo, Yi Xie, Wan-Yun Ling et al.· 0 citations
This paper argues that zero-shot TSF should be governed as an evidence-access claim and proposes a source-first taxonomy that separates three primary evidence sources---frozen LLM prior reuse, parametric time-series pretraining, and retrieval-augmented external memory---from the architectures that implement them.
De-Lu Kong, Wan-Yun Ling, Chen-Xi Liu et al.· 0 citations
CGTime, the 4B-parameter computation-grounded time-series-language model, decoupling perception from description, outperforms far larger general-purpose models on multivariate understanding tasks and attains the best multivariate fact score on a held-out benchmark.
Xinran Feng, Yi Xie, Chao Zhang et al.· 1 citation· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.