Tag
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.
This paper studies how LLM adaptation strategies (definitions, examples, fine-tuning) transfer under source shift in climate disclosure classification, finding that simpler strategies like definitions transfer more consistently than complex ones.
Proposes a decoupled training strategy that adapts normalization layers and uses precomputed features to reduce overhead in transfer learning, achieving competitive accuracy with significantly reduced training time and energy consumption.
This paper presents a strategy to adapt an open-source spoken language model to the Singaporean Home Team context using LoRA fine-tuning, a surrogate text-QA dataset, and a multi-task objective, achieving competitive performance across five speech tasks in Singapore's four official languages.
RAGU is an open-source multi-step GraphRAG engine that uses a compact 7B fine-tuned LLM (Meno-Lite-0.1) to achieve high-quality knowledge graph construction at a fraction of the cost of larger models, outperforming larger systems on benchmarks.
This paper proposes using Group Relative Policy Optimization (GRPO) for adapting LLM-based ASR models to regulated domains using only synthetic speech, achieving 40-45% relative WER reduction over supervised fine-tuning.
Proposes ROAM, a framework that uses LLM world knowledge and reasoning to adapt frozen specialist models to unseen scenarios without retraining, achieving over 20% MAE reduction with minimal overhead.
This paper investigates temporal out-of-distribution shift in deep-learning-based climate downscaling and proposes a domain-adaptive framework that combines supervised reconstruction with domain alignment to improve high-resolution climate projections under non-stationary conditions.
This paper proposes domain adaptation of Sentence Transformer models to automate the mapping between cloud security controls and technical metrics, achieving significant performance gains over zero-shot baselines on control-to-metric and cross-standard association tasks.
This paper investigates whether explicit domain adaptation methods are beneficial for sentiment transfer when using frozen pre-trained language model backbones, finding that effectiveness depends on whether the backbone already possesses target-domain knowledge.
This paper addresses the challenge of predicting thermal volatility in high-performance EV powertrains under real-world loads by applying weighted conformal prediction, achieving modest improvements in coverage under covariate shift.
KARMA proposes a knowledge graph-based approach to generate slot-aligned contrastive candidates and uses Slot-Parallel Alignment (SPA) to apply preference optimization at the entity-slot level, addressing the Resolution Mismatch Problem in LLM reasoning supervision.
PRISM is a novel framework for cross-subject EEG emotion recognition that combines prioritized channel importance weighting via a lightweight expert ensemble with semi-supervised domain adaptation using confidence-filtered pseudo-labels, achieving state-of-the-art results on DEAP, DREAMER, and SEED datasets.
Introduces AnyGroundBench, a domain-adaptation benchmark for spatio-temporal video grounding, evaluating 15 VLMs across five specialized domains and finding current models fail in zero-shot and in-context learning adaptation.