Federated learning (FL) is a promising research paradigm that enables collaborative model training across distributed clients without data sharing. To handle unlabeled data in local clients, existing unsupervised FL research has primarily focused on tasks like clustering and self-supervised representation learning, lea...
Jian Liang, Kuang-Pu Guo, Ran He et al.· 0 citations
This work introduces WorldSolver, a benchmark of 168 simulation tasks derived from physical phenomena in 61 classic computer graphics papers, spanning 7 physical domains, and evaluates them along three dimensions: Execution Checks for successful execution, Visual Fidelity for reproducing the intended dynamic behavior i...
Si-Ru Jiang, Yongzhe Lyu, Shuo Lu et al.· 0 citations
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...
Dong Yan, Jian Liang, Dapeng Hu et al.· 1 citation
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.
Si-Ru Jiang, Yu-Wei Liang, Jian Liang et al.· 1 citation
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...
Siru Jiang, Jian Liang, Ran He et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.