LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2607. 03663v1 Announce Type: cross Abstract: The accurate estimation of Above-Ground Biomass (AGB) in mature tropical forests remains a critical challenge in remote sensing, primarily due to the saturation of Synthetic Aperture Radar (SAR) signals in high-density areas and persistent cloud cover affecting optical imagery.
arXiv:2509. 19833v4 Announce Type: replace-cross Abstract: The United Nations' Sustainable Development Goals (SDGs) provide a globally recognised framework for addressing major societal, environmental, and economic challenges.
arXiv:2607. 03770v1 Announce Type: cross Abstract: Prior studies have demonstrated that diffusion classifiers achieve robust zero-shot classification performance.
arXiv:2603. 11475v2 Announce Type: replace Abstract: Accurate prediction of multivariate time series is essential for emerging network intelligent control, observability, and management functions.
arXiv:2505. 24415v2 Announce Type: replace-cross Abstract: Automated evaluation of movement quality can enhance physiotherapeutic treatment and sports training by providing objective, real-time feedback.
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
arXiv:2607. 03763v1 Announce Type: cross Abstract: Federated Transformer training increasingly relies on local AdamW, whose adaptive updates can provide much stronger local progress than SGD-based training.
arXiv:2607. 04809v1 Announce Type: cross Abstract: Tabular Foundation Models (TFMs) have demonstrated strong empirical performance as black-box inference engines through in-context learning.
arXiv:2607. 03478v1 Announce Type: new Abstract: Post-training of frontier language models is conducted on curated task suites, and inevitably leaves a distribution shift between training and deployment environments.
arXiv:2607. 03530v1 Announce Type: new Abstract: We introduce MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal LLMs (MLLMs) with an executable mechanism for "mental" visualization.
arXiv:2607. 04071v1 Announce Type: cross Abstract: Portuguese remains underrepresented in text embedding evaluation, despite being one of the most widely spoken languages in the world.
arXiv:2604. 05336v2 Announce Type: replace Abstract: Models often fail to complete agentic tasks because they lack core capabilities required by the target environment.
arXiv:2607. 04733v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities.
arXiv:2604. 09544v2 Announce Type: replace-cross Abstract: Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that generalizes broadly.
arXiv:2604. 17376v2 Announce Type: replace-cross Abstract: In today's day and age, we face a challenge in detecting deepfake images because of the fast evolution of modern generative models and the poor generalization capability of existing methods.
arXiv:2512. 15765v3 Announce Type: replace Abstract: Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multiple sources.
arXiv:2607. 04510v1 Announce Type: cross Abstract: Emergent misalignment (EM) -- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data -- is mediated in Qwen2.
arXiv:2507. 18366v2 Announce Type: replace Abstract: Accurate uncertainty quantification remains a key challenge for standard LLMs, prompting the adoption of Bayesian and ensemble-based methods.
arXiv:2602. 06358v3 Announce Type: replace-cross Abstract: We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapters for large language models (LLMs).
Camera intrinsics are vital for recovering 3D structure from 2D video. However, most 3D algorithms assume fixed intrinsics throughout a video, an assumption that often fails for real-world in-the-wild videos.