LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2606. 27304v1 Announce Type: new Abstract: Guided wave-based structural health monitoring (GWSHM) with onboard transducers offers significant potential for the early diagnosis of damage in engineering structures.
arXiv:2606. 26290v1 Announce Type: cross Abstract: While parameter-efficient fine-tuning (PEFT) typically targets attention projectors, its efficacy for tasks requiring sequential state accumulation remains under-explored.
arXiv:2606. 26112v1 Announce Type: cross Abstract: Low-resource languages face a critical challenge in AI development: creating specialized conversational systems without access to massive training corpora.
arXiv:2606. 26552v1 Announce Type: cross Abstract: The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread dissemination of highly realistic AI-generated images.
arXiv:2606. 26595v1 Announce Type: new Abstract: Enhancing the analysis of service feedback is essential for public sector organizations, particularly tax administrations, where trust and compliance depend on fair and effective service delivery.
Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fluent while drifting from the ground-truth dynamics. We hypothesize that hallucination concentrates in low-coverage regions of the state-action space, where lightweight data-centric signals can both detect it and guide mitigation.
Reinforcement learning from human feedback (RLHF) for 3D generation is now established across a number of works, but most existing pipelines optimise explicit surface representations, often by converting radiance fields into meshes and training heavily on surface-supervised data. We instead fine-tune a pretrained 3D-aware generative model directly from a learned reward over radiance-field density ($σ$) values, with no externally supplied mesh or shape prior.
Guided wave-based structural health monitoring (GWSHM) with onboard transducers offers significant potential for the early diagnosis of damage in engineering structures. However, the practical deployment of deep learning models is often hindered by the limited availability of labelled experimental data and the high computational cost of generating large-scale high-fidelity simulation datasets.
Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens. These tokens are derived from a codebook that maps embeddings to quantized visual patterns.
Legal outcome prediction must disentangle objective case facts from adjudicative context. Merit-based rulings rely on factual evidence while technical disposals may hinge on judicial discretion.
Existing facial expression quality assessment (FEQA) methods typically produce only a severity score, without explicitly communicating the observable facial motion evidence that supports the prediction. This limits interpretability and makes it difficult to inspect the basis of model outputs in Parkinson's disease assessment.
Embedding-based retrieval ranks items by their similarity to a query in a shared vector space and usually aims to return the highest-scoring items. In many production settings this is not what is wanted: given a seed set that expresses a fine-grained pattern, one needs more items that both satisfy a target attribute and stay within that pattern.
Supervised fine-tuning (SFT) on a small, high-quality set of long reasoning traces is an effective approach for eliciting strong reasoning capabilities in Large Language Models (LLMs). However, existing methods for curating high-quality SFT data rely heavily on strong reasoning models to filter examples based on diversity and difficulty, making the curation process costly while often yielding suboptimal data quality.
arXiv:2507. 16518v3 Announce Type: replace-cross Abstract: Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities.
arXiv:2606. 25964v1 Announce Type: cross Abstract: Small ($\sim$2B) GUI-grounding agents are attractive for on-device deployment, accessibility tooling, and low-cost iteration, but at this scale they face two open recipe questions: how to obtain bounding-box training data without expensive human annotation, and how to combine supervised fine-tuning with reinforcement learning.
arXiv:2606. 24954v1 Announce Type: new Abstract: Vibration-based health monitoring of rotating machinery requires reliable fault diagnosis under operational data constraints, yet condition assessment remains challenged by structural scarcity of fault events and heterogeneous sim-to-real gaps in digital twin-generated signals.
arXiv:2606. 24937v1 Announce Type: cross Abstract: The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems.
arXiv:2606. 24950v1 Announce Type: new Abstract: Financial decision-making is contextual: forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamentals, macroeconomic regime, and contemporaneous text.
arXiv:2606. 25450v1 Announce Type: new Abstract: Traditional evaluations measure a learning algorithm's final performance on an i.
arXiv:2510. 04773v2 Announce Type: replace Abstract: As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention.