domain-adaptation

Tag

Cards List
#domain-adaptation

Rectifying Geometric Misalignment: Online Source-Free Adaptation for Class-Imbalanced EEG

arXiv cs.LG · 6d ago Cached

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.

0 favorites 0 likes
#domain-adaptation

Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study

arXiv cs.CL · 2026-08-04 Cached

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.

0 favorites 0 likes
#domain-adaptation

Recognition and Label-Free Adaptation Across Recording Sessions in Surface-EMG Gesture Decoding

arXiv cs.LG · 2026-07-31 Cached

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.

0 favorites 0 likes
#domain-adaptation

Domain adaptation for handwriting trajectory reconstruction from IMU sensors

arXiv cs.LG · 2026-07-30 Cached

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.

0 favorites 0 likes
#domain-adaptation

Voice Memory for Agentic Speech Recognition

arXiv cs.CL · 2026-07-30 Cached

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.

0 favorites 0 likes
#domain-adaptation

Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance

arXiv cs.CL · 2026-07-28 Cached

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.

0 favorites 0 likes
#domain-adaptation

Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits

arXiv cs.LG · 2026-07-27 Cached

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.

0 favorites 0 likes
#domain-adaptation

What Transfers Under Source Shift? Definitions, Examples, and Fine-Tuning for Climate Disclosure Classification

arXiv cs.CL · 2026-07-21 Cached

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.

0 favorites 0 likes
#domain-adaptation

Beyond Backbone Backpropagation: A Decoupled Strategy for Efficient Transfer Learning

arXiv cs.LG · 2026-07-16 Cached

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.

0 favorites 0 likes
#domain-adaptation

Efficiently Adapting Spoken Language Models for the Singaporean Context

arXiv cs.CL · 2026-07-14 Cached

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.

0 favorites 0 likes
#domain-adaptation

RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM

Hugging Face Daily Papers · 2026-07-13 Cached

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.

0 favorites 0 likes
#domain-adaptation

When Synthetic Speech Is All You Have: Better Call GRPO

arXiv cs.CL · 2026-07-10 Cached

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.

0 favorites 0 likes
#domain-adaptation

Open-Ended Scenario Reasoning for Specialist Model Adaptation

arXiv cs.LG · 2026-07-09 Cached

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.

0 favorites 0 likes
#domain-adaptation

Domain-Adaptive Climate Downscaling Under Temporal Distribution Shift

arXiv cs.LG · 2026-07-08 Cached

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.

0 favorites 0 likes
#domain-adaptation

Automated Compliance Mapping in Cloud Security with Domain-Adapted Sentence Transformers

arXiv cs.CL · 2026-07-08 Cached

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.

0 favorites 0 likes
#domain-adaptation

Is Domain Adaptation Always Helpful? A Frozen-Backbone Study of Cross-Domain Sentiment Transfer

arXiv cs.CL · 2026-07-08 Cached

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.

0 favorites 0 likes
#domain-adaptation

Weighted Conformal Prediction for Lab-to-Track Thermal Transfer in EV Motorsport Powertrains

arXiv cs.LG · 2026-07-07 Cached

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.

0 favorites 0 likes
#domain-adaptation

KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment

arXiv cs.CL · 2026-07-07 Cached

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.

0 favorites 0 likes
#domain-adaptation

PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition

arXiv cs.LG · 2026-07-02 Cached

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.

0 favorites 0 likes
#domain-adaptation

AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models

Hugging Face Daily Papers · 2026-07-02 Cached

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.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback