Tag
This paper proposes RMemSafe, a reliability-gated extension for continual test-time adaptation that attenuates source anchoring when the frozen source's predictive entropy becomes high, preventing blind anchoring under source collapse. The method achieves state-of-the-art error reduction on the CCC benchmark.
This paper introduces SCOPE-Bench, a benchmark for evaluating molecular out-of-distribution generalization, and POMA, a framework using reinforcement learning to select source domains for domain adaptation, achieving significant error reductions on 3D molecular models.
This paper demonstrates that switching from Masked Language Modeling to Causal Language Modeling during encoder adaptation improves downstream performance on biomedical texts. The authors release ModernBERT-bio and ModernCamemBERT-bio as state-of-the-art biomedical encoders.
This paper introduces STDA-Net, a domain adaptation framework for cross-dataset sleep stage classification using 2D spectrograms and adversarial learning. It demonstrates improved accuracy and stability over existing 1D EEG baseline methods on public datasets.
This paper proposes a locality-aware private class identification approach and a reliable optimal transport-based method (ReOT) to address domain adaptation challenges under extreme label shift, particularly distinguishing shared from private classes.
This paper presents Qatar University's multi-stage QLoRA fine-tuning approach on Qwen3-4B for Arabic Islamic inheritance reasoning, achieving 90% MIR-E score through domain adaptation on Islamic fatwa records followed by task-specific training on 12,000 structured inheritance cases, matching commercial systems like Gemini-2.5-flash with minimal computational resources.
JFinTEB introduces the first comprehensive benchmark for evaluating Japanese financial text embeddings, addressing a gap in domain-specific and language-specific evaluation resources. The benchmark includes retrieval and classification tasks evaluated across Japanese-specific, multilingual, and commercial embedding models, with datasets and evaluation framework publicly released.
OpenAI researchers demonstrate a method to bridge the reality gap in robotic control by training policies with randomized simulator dynamics, enabling robots trained purely in simulation to successfully transfer to real-world tasks like object manipulation without physical training.
OpenAI presents a method for unsupervised third-person imitation learning that enables agents to learn from demonstrations taken from different viewpoints without explicit state correspondence, using domain confusion techniques to learn viewpoint-agnostic features.