HullFT performs test-time finetuning by sparse convex reconstruction of query embeddings followed by gradient caching on repeated examples, yielding better quality-efficiency tradeoffs than prior TTFT methods.
Robustness is a function, not a number: A factorized compre- hensive study of OOD robustness in vision-based driving.arXiv preprint arXiv:2602.09018, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching
HullFT performs test-time finetuning by sparse convex reconstruction of query embeddings followed by gradient caching on repeated examples, yielding better quality-efficiency tradeoffs than prior TTFT methods.