Papers Domain Adaptation
“Domain Adaptation” 태그가 달린 논문 7,141편 · 필터 해제
HuatuoGPT-3: RL-Only Domain Adaptation from Base Models
Domain adaptation aims to turn a general-purpose large language model (LLM) into an expert for a target domain. While the dominant SFT+RL pipeline offers a convenient cold start, it may reduce exploration diversity and i…
Domain AdaptationWeather-Aware Domain Adaptation for Street-View Weather Recognition
Adverse conditions such as rain, snow, fog, and dust remain challenging for camera-based perception in autonomous driving. We study multi-class weather recognition from street-view images under domain shift, where most a…
Autonomous DrivingDomain AdaptationMapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
Large Language Models (LLMs) have demonstrated remarkable fluency across many tasks but remain limited by their static, parameter bound knowledge and their susceptibility to hallucinating information. Retrieval Augmented…
Reinforcement LearningDomain AdaptationSee it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs
Safety-aligned LLMs can exhibit emergent misalignment (EM): narrow domain adaptation unexpectedly triggers catastrophic safety failures across unrelated domains. Prior static analyses leave training dynamics unmapped, wh…
Domain AdaptationBeyond In-Distribution Metrics: A Systematic Out-of-Distribution Evaluation of Congenital Heart Disease Segmentation
Congenital heart disease (CHD) diagnosis and surgical planning often require patient-specific 3D anatomical models, but manual segmentation is labor-intensive, particularly in complex anatomies. Although deep-learning me…
Domain AdaptationAVSRBench: A Multi-Condition AVSR Benchmark
While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true generalization or just domain adaptation. To investigate this gap, we e…
Domain GeneralizationDomain AdaptationRiLM: Parameter-Efficient Language Modeling via Geodesic Decoding
Language models under one million parameters matter for edge deployment, domain adaptation, and reproducible research, yet a two-layer LSTM or Transformer at embedding width d = 128 still spends roughly one third of its …
Domain AdaptationMulti-Pass, Multi-View Blended Learning for High-Fidelity Volumetric CT Synthesis from Chest X-Rays
Reconstructing volumetric Computed Tomography (CT) from a single 2D chest radiograph (CXR) is an ill-posed inverse problem, further complicated by the scarcity of paired CXR-CT training data. Prior approaches address thi…
Domain AdaptationTransfer LearningArti-JEPA: Adapting Video World Model to Real-Time MRI of the Vocal Tract for Speech-Production Analysis
Real-time MRI (rtMRI) captures the dynamics of the entire vocal tract during speech, but labeled data are scarce and the modality - single-slice, grayscale, low-resolution - differs substantially from the natural videos …
Domain AdaptationNCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction
We introduce NCP-ArchPreview, a latent-space language model that pushes autoregressive pretraining beyond standard next-token prediction (NTP). Alongside NTP, the model learns through Next Concept Prediction (NCP) to pre…
Domain AdaptationWhen Financial Fine-tuning Fails: A Three-Level Detectability Analysis of Numerical Hallucination in Domain-Adapted Language Models
Financial large language models are increasingly deployed for summarization of reports and disclosures, where numerical hallucination poses significant practical risks. While prior work often attributes such hallucinatio…
Domain AdaptationDesigning an Auditable LLM-Supported Workflow for Qualitative Thematic Analysis
Large Language Models (LLMs) offer new possibilities for scaling qualitative analysis, but existing applications often provide limited methodological transparency regarding how qualitative methods are translated into com…
Domain AdaptationSelf-Supervised Pretext Tasks for Infant Cry Analysis: A Controlled Comparison and a Cautionary Result on Donateacry
We compare six self-supervised pretext tasks for infant cry analysis under a fixed budget, meaning the same compact encoder of 1.17M parameters, the same 115 hours of license-verified public pretraining audio, and the sa…
Domain AdaptationMotus2: A Self-Evolving General World Model for Dexterous Manipulation
General embodied agents should perceive, predict, act, evaluate, and improve within a unified system. World models have shown great promise in building such agents, yet existing models typically append an action output h…
Domain AdaptationCPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation
Supervised fine-tuning (SFT) is the de facto standard for adapting large language models (LLMs) to target domains, but it often degrades the model's general capabilities, a phenomenon known as catastrophic forgetting. Ex…
Domain AdaptationDual-Stream Semantic Guidance with Prototype Anchor Calibration for Source-Fully-Free Adaptation of Vision-Language Models
Source-Fully-Free Domain Adaptation (SFF-DA) has emerged as a strategic paradigm to adapt Vision-Language Models (VLMs) without any access to source data or task-specific source models. However, we identify a critical Du…
Knowledge DistillationDomain AdaptationThomson: Continual Learning of Frontier Models for SovereignAI
The development of frontier models is commonly perceived to be the exclusive remit of a small number of heavily funded players, creating an information, economic and power asymmetry between developers and the diverse use…
Continual LearningPrompt EngineeringDomain AdaptationFast Generative Grasping via Lie Group-Constrained MeanFlow
Grasp synthesis is a core task in robotic manipulation, for which the solution typically forms a multimodal distribution rather than a point estimate. Generative robotic grasping aims to learn this distribution with deep…
Domain AdaptationRobotic GraspingConformal Risk Minimization for Semi-Supervised Domain Adaptation via Optimal Transport
In high-stakes healthcare applications, machine learning models are frequently trained on data from one patient population and deployed on another, creating a distribution shift that degrades both accuracy and reliabilit…
Skin Lesion ClassificationDomain AdaptationKnowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation
Supervised fine-tuning (SFT) can degrade factual behavior outside the target domain. This degradation is often described as catastrophic forgetting, yet open-ended factual failures do not necessarily imply that the under…
Domain Adaptation