domain-adaptation

This paper introduces Transported Conformal Calibration (TCC), a method to transfer conformal prediction calibration from a labeled source domain to an unlabeled target domain using paired observations, ensuring coverage guarantees with label-free diagnostics.

This paper introduces a data-centric pipeline for post-training language models to enhance financial reasoning through mining reasoning traces, distilling instruction data, and generating verifiable QA pairs, demonstrating improvements in performance while preventing catastrophic forgetting.

This paper proposes a zero-shot learning framework for multivariate IoT traffic anomaly detection using adversarial and contrastive learning within a variational autoencoder, enabling domain adaptation without labeled data and demonstrating strong performance across diverse datasets.

DRET is a parameter-efficient knowledge-transfer method that injects biomedical domain knowledge into smaller models like DistilBERT via embedding transfer, achieving performance competitive with larger specialized models.

This paper introduces SpeakPay and a Nepali financial speech dataset, showing that LoRA fine-tuning of Whisper reduces Word Error Rate by 67.2% and improves transaction success rates for low-resource language accessibility.

This paper proposes ReNC, a method for open-world test-time adaptation that leverages neural collapse as a structural prior to filter out-of-distribution samples and refine prototypes for reliable model adaptation.

This paper addresses the challenges of domain adaptation in physics, where simulations differ from experimental data in nuisances and label shifts. It proposes adaptive domain adaptation to focus on genuine physical mismatches and provides a model selection rule.

This paper benchmarks pretrained molecular language models for virtual screening and demonstrates that explicit domain adaptation improves their performance and sample efficiency across drug discovery, materials, and catalysis libraries.

This paper presents a validated adaptation protocol for label-free drone-based crowd counting to ensure safety at mass events like the 2034 FIFA World Cup in Saudi Arabia, addressing domain shift and deployment challenges.

Forward-Pass-Only MLP training (FPO) adapts large language models without backpropagation, achieving 2.7–3.2× higher throughput and 40% less peak memory while maintaining benchmark performance.

This paper introduces RAEF, a model-agnostic retrieval-augmented method for time series forecasting that improves accuracy and reduces computational overhead compared to fine-tuning approaches.

StreamHear is a semi-supervised pipeline that adapts streaming speech recognition to domain-shifted audio by fine-tuning a teacher model on labeled data, generating pseudo-labels for unlabeled data, and fine-tuning a student model, with a realignment step for better word placement.

The paper proposes TELLME, a test-enhanced learning method for continual pre-training of LLMs, which improves domain-specific knowledge acquisition and long-term memory retention, outperforming existing methods in the financial domain.

This paper proposes OSPDIM, a source-free online unsupervised domain adaptation framework for EEG-based BCIs that corrects geometric misalignment caused by class-imbalanced label shifts on the Riemannian manifold, outperforming standard alignment methods in online scenarios.

A systematic cross-architecture empirical study measuring the trustworthiness cost of domain adaptation in small language models, finding that safety-preserving fine-tuning strategies do not reliably transfer alignment.

This paper introduces a montage-agnostic encoder for surface-EMG gesture decoding that maintains recognition accuracy across recording sessions without recalibration, and shows that feature-statistic alignment at test time improves adaptation on NinaPro DB6.

This paper proposes a domain adaptation approach for handwriting trajectory reconstruction from IMU sensors, addressing signal differences between adult and children's handwriting to improve reconstruction accuracy for educational applications.

Voice Memory introduces an inference-only scheme for agentic speech recognition where a frozen corrector uses a per-domain memory file to decide per utterance whether to act or abstain, reducing word error rate across multiple domains without weight updates.

Earnings25 is a 500-hour benchmark for evaluating automatic speech recognition on financial earnings calls, providing aligned transcripts and structured metadata for speaker- and industry-aware evaluation.

This paper introduces cross-domain off-policy evaluation and learning (OPE/L) for contextual bandits, allowing the use of logged data from multiple source domains to improve policy evaluation and learning in target domains with challenging conditions like few-shot data, deterministic logging policies, and new actions.