domain-adaptation

Tag

Cards List
#domain-adaptation

Reliability-Gated Source Anchoring for Continual Test-Time Adaptation

arXiv cs.LG · 2026-05-15 Cached

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.

0 favorites 0 likes
#domain-adaptation

Rethinking Molecular OOD Generalization via Target-Aware Source Selection

arXiv cs.LG · 2026-05-15 Cached

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.

0 favorites 0 likes
#domain-adaptation

A Causal Language Modeling Detour Improves Encoder Continued Pretraining

Hugging Face Daily Papers · 2026-05-12 Cached

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.

0 favorites 0 likes
#domain-adaptation

STDA-Net: Spectrogram-Based Domain Adaptation for cross-dataset Sleep Stage Classification

arXiv cs.LG · 2026-05-11 Cached

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.

0 favorites 0 likes
#domain-adaptation

Locality-aware Private Class Identification for Domain Adaptation with Extreme Label Shift

arXiv cs.AI · 2026-05-08 Cached

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.

0 favorites 0 likes
#domain-adaptation

QU-NLP at QIAS 2026: Multi-Stage QLoRA Fine-Tuning for Arabic Islamic Inheritance Reasoning

arXiv cs.CL · 2026-04-21 Cached

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.

0 favorites 0 likes
#domain-adaptation

JFinTEB: Japanese Financial Text Embedding Benchmark

arXiv cs.CL · 2026-04-20 Cached

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.

0 favorites 0 likes
#domain-adaptation

Sim-to-real transfer of robotic control with dynamics randomization

OpenAI Blog · 2017-10-18 Cached

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.

0 favorites 0 likes
#domain-adaptation

Third-person imitation learning

OpenAI Blog · 2017-03-06 Cached

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.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback