LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2509. 07829v4 Announce Type: replace-cross Abstract: Literary translation has recently gained attention as a distinct and complex task in machine translation research, yet translation by small open models remains an open problem, particularly for low-resource languages such as Romanian.
arXiv:2604. 27720v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly applied to medical visual question answering (Med-VQA), yet whether they can \emph{localize} the evidence behind their answers---a prerequisite for clinical auditability---is poorly characterized.
arXiv:2607. 25887v1 Announce Type: cross Abstract: This paper explores the effectiveness of domain adaptation techniques when using convolutional neural network (CNN)-based and transformer-based feature representations for acoustic scene classification.
arXiv:2607. 25108v1 Announce Type: cross Abstract: Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, protocols, and patient populations.
arXiv:2607. 24898v1 Announce Type: cross Abstract: State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety guidelines to all users.
arXiv:2607. 24845v1 Announce Type: cross Abstract: Large language models (LLMs) have been applied to sequential recommendation by formulating it as a natural language task.
arXiv:2607. 24799v1 Announce Type: cross Abstract: Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning.
arXiv:2607. 24791v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is the dominant paradigm for applying large language models (LLMs) to enterprise document corpora, yet naive implementations encounter hard limits as corpus scale and query complexity grow.
arXiv:2607. 24745v1 Announce Type: cross Abstract: Key Information Extraction (KIE) is vital for many document applications, but creating training datasets is traditionally a time-consuming manual process.
arXiv:2607. 25728v1 Announce Type: cross Abstract: This paper presents a cooperative indoor UAV guidance framework that combines a shared voxel-map world model with a multi-agent Soft Actor-Critic (MASAC) controller.
arXiv:2607. 25157v1 Announce Type: new Abstract: Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretraining with bidirectional denoising.
arXiv:2607. 25091v1 Announce Type: new Abstract: The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms have not been systematically investigated.
arXiv:2607. 24814v1 Announce Type: new Abstract: Access to specialist clinical expertise remains severely limited across sub-Saharan Africa, where physician-to-patient ratios can fall below 1:25,000 in rural settings.
arXiv:2607. 25292v1 Announce Type: new Abstract: Silicon sampling uses language models as proxies for human survey respondents, treating each model call as an independent draw from the persona's response distribution.
Plant biosynthetic gene clusters (BGCs) encode specialized-metabolite pathways, yet curated plant BGC labels remain scarce, hindering supervised discovery at genome scale. Existing plant BGC mining tools are largely signature- and rule-driven and do not fully leverage recent advances in contextual representation learning for modeling long-range domain context and controlling false positives under strong domain shift.
Financial disclosures contain numerical claims, temporal statements, entity references, policy commitments, and risk descriptions that may conflict in qualitatively different ways. Detecting a conflict is only the first step: review workflows may also need to determine its type, since numerical, temporal, referential, factual, and normative inconsistencies require different evidence and downstream checks.
Reinforcement learning (RL) fine-tuning is widely used in language model training to improve model performance on a target task while limiting drift from a reference policy. A standard way to balance this trade-off is via a KL-regularized RL objective, although this formulation does not by itself provide a principled way to set the regularization coefficient.
Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised fine-tuning (SFT) to pursue the same underlying goals.
Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting language models under tight compute budgets, yet their interaction is most often studied on billion-parameter models where the design space is expensive to explore. We ask a complementary question: on a specific, fully reproducible 60M-parameter encoder-decoder model (T5-small) and a single-table text-to-SQL benchmark (WikiSQL), how much task accuracy does each efficiency knob actually cost?
arXiv:2607. 22637v1 Announce Type: new Abstract: Deep learning has shown strong potential for massive multiple-input multiple-output (Massive MIMO) physical-layer tasks, including channel state information (CSI) feedback and channel estimation.