We have 4 of 46 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.
Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping the matrices dense, and thus efficient on standard hardware. Existing methods, however, choose the subspace to remove from each weight matrix with local closed-form crit...
The 10th AI City Challenge, held with ECCV 2026, marks a decade of community benchmarking for intelligent transportation, smart cities, and physical AI with 325 registered teams, and participation from 26 countries and regions, up from 15.
This work introduces XTC (Exclude Top Choices), a lightweight head-aware decoding operator that targets this regime of open-ended generation in which several continuations are plausible but too much probability mass remains concentrated on the most generic choice.
Large Language Models generate text autoregressively, but open-ended generation is prone to verbatim looping, in which models repeat spans already present in context. Standard defenses such as repetition, presence, and frequency penalties and n-gram blocking act on token recurrence rather than the sequential structure...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
