Domain Adaptation

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 Generalization Domain Adaptation

RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding

2026-09-09 · Fang Li arxiv

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 Adaptation

Multi-Pass, Multi-View Blended Learning for High-Fidelity Volumetric CT Synthesis from Chest X-Rays

2026-09-09 · Ozer Can Devecioglu, Serkan Kiranyaz, Rashid Mazhar, Tahir Hamid 외 arxiv

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 Adaptation Transfer Learning

Arti-JEPA: Adapting Video World Model to Real-Time MRI of the Vocal Tract for Speech-Production Analysis

2026-09-09 · Hong Nguyen, Sean Foley, Christina Hagedorn, Yijing Lu 외 arxiv

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 Adaptation

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

2026-09-09 · NCP Team, Jiaqi Cao, Chiyu Chen, Shuang Cheng 외 hf

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 Adaptation

When Financial Fine-tuning Fails: A Three-Level Detectability Analysis of Numerical Hallucination in Domain-Adapted Language Models

2026-09-04 · Xiaodong Li, Peiwei Liu arxiv

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 Adaptation

전체 7,136편 보기 →