The geometry of semantic embeddings is studied by studying the geometry of semantic embeddings to trace a clear failure mode: features that determine the neighbors of unseen prompts are an unreliable proxy for LLM selection.
Leonardo Torti, Emanuele Rimoldi, Tomer Galanti et al.· 0 citations
Large language models are generally more capable than smaller ones, but their memory requirements can make local deployment difficult. We ask whether part of this capability gap can instead be recovered by running a smaller or more compressed model multiple times and selecting among its outputs using public or model-ge...
Tomer Galanti, Josh M. Susskind, Eran Malach· 0 citations
Finding the right video often requires distinguishing similar scenes in which different events occur. Joint matching improves retrieval, but processing rich video representations for each query is costly. VEDJE compresses features within sampled frames while keeping their representations separate in a reusable cache. F...
S. Wagner, Gabriele Serussi, D. Ben-Ami et al.· 1 citation
Same-instance self-supervised learning (SSL) learns representations by enforcing consistency across two views of the same underlying instance. This principle alone, however, does not determine which downstream tasks remain recoverable from the learned representation. We study this question through \emph{semantic recove...
Achleshwar Luthra, Lucas Bryant, T. Zhu et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.