We have 3 of 23 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.
Quantizer-Aligned Recalibration (QuAR), a single-pass TTA method tailored to quantized ViTs that neither backpropagates nor updates any model parameters is proposed, which achieves the highest mean accuracy among state-of-the-art backpropagates nor updates any model parameters.
Most KV-cache eviction methods ask, in effect, which memory appeared important while reading the prompt? We instead ask which memory will matter while answering? Since decoding queries are unavailable at eviction time, prior future-aware methods rely on pseudo-responses or synthetic future-query estimates. We cast fixe...
Although compressed models retain high accuracy under supervised adaptation, their TTA performance degrades significantly with increasing compression, highlighting the need to design compression strategies that preserve adaptability.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
