LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2607. 05400v1 Announce Type: cross Abstract: Generative AI models, such as Large Language Models (LLMs) and diffusion models, have demonstrated impressive performance across a wide range of tasks.
arXiv:2510. 07364v4 Announce Type: replace Abstract: What do thinking language models learn during training that their base models lack?
arXiv:2607. 05645v1 Announce Type: new Abstract: Deep-learning-based climate downscaling aims to learn relationships from historical low-resolution (LR) and high-resolution (HR) climate data to generate HR climate projections.
arXiv:2607. 06527v1 Announce Type: cross Abstract: Multi-hop Question Answering over Knowledge Graphs faces a critical challenge: traditional retrieve-then-read pipelines break differentiability, preventing the retriever from learning to bridge the semantic gap where intermediate nodes lack lexical overlap with the query.
arXiv:2509. 11819v2 Announce Type: replace Abstract: Federated Domain Adaptation (FDA) is a federated learning (FL) approach that improves model performance at the target client by collaborating with source clients while preserving data privacy.
arXiv:2607. 05898v1 Announce Type: new Abstract: Evaluating whether unlearning algorithms truly remove training data influence remains an open challenge.
arXiv:2506. 01544v2 Announce Type: replace Abstract: We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient and accurate individualized imputation and forecasting.
arXiv:2607. 05711v1 Announce Type: new Abstract: Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications.
arXiv:2512. 18542v3 Announce Type: replace-cross Abstract: AI coding assistants produce vulnerable code in 45\% of security-relevant scenarios~\cite{veracode2025}, yet no public training dataset teaches both traditional web security and AI/ML-specific defenses in a format suitable for instruction tuning.
arXiv:2607. 02567v2 Announce Type: replace-cross Abstract: Radio frequency fingerprint identification (RFFI) provides a physical-layer credential for Internet of Things devices, but open-set decisions become fragile when a threshold calibrated on a source receiver is applied to a target receiver.
arXiv:2607. 05910v1 Announce Type: cross Abstract: Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image.
arXiv:2607. 05615v1 Announce Type: new Abstract: Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning, but standard methods apply the steering signal at every generated token, incurring constant per-token perturbation that risks degrading fluency.
arXiv:2607. 05937v1 Announce Type: cross Abstract: Sentiment analysis with frozen pre-trained language model (PLM) backbones has become a common paradigm, yet the practical benefit of explicit domain adaptation remains unclear, particularly when backbones encode varying degrees of target-domain knowledge.
arXiv:2607. 05752v1 Announce Type: cross Abstract: Search-augmented language models can use external evidence to compensate for limitations in parametric knowledge, but search is not uniformly beneficial: models may call search for questions they can already answer, or rely on noisy evidence when correction, clarification, or abstention would be more appropriate.
arXiv:2607. 06175v1 Announce Type: cross Abstract: Large language models (LLMs) can generate BPMN process models from natural-language descriptions, yet supervised fine-tuning (SFT) limits their output quality to the patterns present in the training data.
arXiv:2607. 06233v1 Announce Type: new Abstract: LLM-powered data agents are playing an increasingly important role in data-driven decision making.
arXiv:2607. 05568v1 Announce Type: cross Abstract: Representing 3D shapes as compact sets of geometric primitives is fundamental to robotics, simulation, and scene understanding.
arXiv:2607. 05658v1 Announce Type: cross Abstract: Global Navigation Satellite Systems (GNSS), best known for positioning, also serve weather science, as atmospheric water vapour delays their signals.
arXiv:2607. 06125v1 Announce Type: cross Abstract: Neural decompilation is increasingly studied as a code-generation problem, yet its evaluation methodology remains underdeveloped for modern languages.
arXiv:2604. 21927v3 Announce Type: replace Abstract: Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge.