新研究探索用于大型语言模型的先进测试时自适应技术

报道来源 [7]

1. arXiv cs.LG TIER_1 English(EN) · Azal Ahmad Khan, Keshav Ramji, Tahira Naseem, Ali Anwar, Ram\'on Fernandez Astudillo · 2026-10-03 04:00

   学习预测权重更新的分布以进行测试时自适应

   arXiv:2610.01934v1 Announce Type: new Abstract: Hypernetworks have recently shown success in dynamically adapting the parameters of Large Language Models (LLMs) at runtime based on signals such as task descriptions or additional demostrations. Here we ask: how much adaptation sig…

2. arXiv cs.LG TIER_1 English(EN) · Abinitha Gourabathina, Hyewon Jeong, Teya Bergamaschi, Marzyeh Ghassemi, Collin Stultz · 2026-10-02 04:00

   Rank-Constrained Adaptation for Reliable Real-World Performance

   arXiv:2602.06924v3 Announce Type: replace Abstract: Deep learning models trained to optimize average accuracy often exhibit systematic failures on particular subpopulations. In real-world settings like healthcare, the subpopulations most affected by such disparities are frequentl…

3. Hugging Face Daily Papers TIER_1 English(EN) · 2026-10-01 16:05

   学习预测权重更新的分布以进行测试时适应

   Hypernetworks have recently shown success in dynamically adapting the parameters of Large Language Models (LLMs) at runtime based on signals such as task descriptions or additional demostrations. Here we ask: how much adaptation signal can be obtained using only the input query t…

4. arXiv cs.AI TIER_1 English(EN) · Tingyu Shi, Fan Lyu, Haihua Zhu, Dadi Wang, Shaoliang Peng · 2026-09-30 04:00

   CPATTA：主动测试时自适应的保形监督分配

   arXiv:2509.25692v2 Announce Type: replace-cross Abstract: Active Test-Time Adaptation (ATTA) improves model robustness under domain shift by selectively querying human annotations at deployment, but existing methods use heuristic uncertainty measures and suffer from low data sele…

5. arXiv cs.AI TIER_1 English(EN) · Muhammad Huzaifa, Lea Sch\"onherr, Thorsten Eisenhofer · 2026-09-30 04:00

   WISE-ATTA：在预算主动测试时间自适应中何时请求标签

   arXiv:2609.37687v1 Announce Type: new Abstract: Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying supervision. However, most existing ATTA methods implicitly assume that supervi…

6. Hugging Face Daily Papers TIER_1 English(EN) · 2026-09-29 00:00

   WISE-ATTA：在预算主动测试时间自适应中何时请求标签

   Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying supervision. However, most existing ATTA methods implicitly assume that supervision can be requested for every incoming test ba…

7. arXiv cs.CV TIER_1 English(EN) · Youjia Zhang, Huiling Liu, Soyun Choi, Jaehong Yoon, Sungeun Hong · 2026-09-30 04:00

   并非所有修正都有益：增益引导的持续测试时适应

   arXiv:2609.36655v1 Announce Type: new Abstract: Continual test-time adaptation (CTTA) adapts a source model to an unlabeled test stream whose distribution may change over time. Existing TTA methods often assess prediction reliability using confidence or entropy, which primarily r…