We have 4 of 24 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.
Motivated by the well-calibrated nature of zero-shot predictions, CoTS is proposed, a simple yet effective post-hoc calibration method that preserves accuracy and enhances both accuracy and calibration simultaneously.
AgentStream is introduced, a unified framework that evaluates self-evolving agents spanning diverse evolution components by organizing agentic benchmarks into a configurable task stream and instantiating the \texttt{Isolated}, \texttt{Sequential}, and \texttt{Interleaved} streaming scenarios at test time, which progres...
This work proposes Cross-Augmentation Similarity (CAS), a simple baseline that performs adaptation only when predictions across augmented views exhibit low similarity, which not only preserves but in some cases improves overall accuracy, even when skipping nearly 85% of the adaptation process.
Test-time adaptation (TTA) has emerged as a popular paradigm for improving the performance of vision-language models (e.g., CLIP) on downstream tasks. Among existing CLIP-based TTA methods, Test-Time Prompt Tuning (TPT) is a pioneering work that optimizes textual prompts using multiple test-time augmentations and remai...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
