LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2608.21385v1 Announce Type: cross Abstract: Social media has become a central arena in which armed conflicts are contested, yet the pro-Israel and pro-Palestine communities on Telegram, whose b...
arXiv:2608.21727v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is deployed to make models better at reasoning tasks, but its side effect on what models will d...
arXiv:2608.21761v1 Announce Type: new Abstract: Large collections of street-view imagery provide rich visual information about urban environments, but extracting fine-grained geographic information f...
arXiv:2608.21673v1 Announce Type: cross Abstract: Longitudinal electronic health records (EHRs) document patients' sequences of clinical visits over time, preserving the temporal evolution of disease...
arXiv:2608.23373v1 Announce Type: new Abstract: Forecasting long-range influenza-like illness (ILI) matters for public health readiness. Publicly available surveillance datasets typically pair numeri...
arXiv:2511.22281v2 Announce Type: replace Abstract: Observing certain patches in an image reduces the uncertainty of others. Their realization lowers the distribution entropy of each remaining patch...
arXiv:2608.21440v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have advanced end-to-end autonomous driving by leveraging foundation models for semantic reasoning and long-tail...
arXiv:2608.23253v1 Announce Type: cross Abstract: Vision-language models typically encode an image into hundreds of visual tokens, incurring substantial inference latency and GPU memory overhead. Exi...
The paper introduces a scalable cross‑domain event extraction system built on a unified generative sequence‑to‑sequence framework. It jointly handles event detection and argument extraction, allowing both pipeline and end‑to‑end configurations. By fine‑tuning pretrained language models on multiple event datasets from diverse domains, the system retains domain‑specific semantics while generalizing across large, evolving label spaces, and offers a web‑based application for researchers to upload documents, extract events, visualize triggers and arguments, and compare configurations.
arXiv:2607.27836v2 Announce Type: replace Abstract: Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recover...
arXiv:2608.21427v1 Announce Type: new Abstract: Tuberculosis (TB) is one of the most common and dangerous bacterial ailments. Every year, it causes a large number of deaths worldwide. Although many d...
arXiv:2608.22789v1 Announce Type: new Abstract: Additive Manufacturing (AM) plays a vital role in the ongoing industrial revolution. However, quality control remains crucial and challenging due to pr...
The paper introduces Segment Anything Small (SAS), a data‑augmentation method that improves deep‑learning segmentation of small anatomical structures in ultrasound images. SAS uses two transformations: resizing and embedding organ thumbnails into a black background to vary organ scale, and adding noise to regions of interest to mimic tissue texture variability. Experiments on one internal and five external datasets show Dice score gains up to 0.35, with an average improvement of 0.16, and demonstrate that SAS enhances model robustness and generalizability without adding hallucinations or artifacts.
arXiv:2608.21756v1 Announce Type: cross Abstract: Deep-learning efforts have increasingly shifted toward foundation model approaches. In experimental physics, this allows models and learned represent...
EG-ARSA introduces an Expert‑Grounded Distillation (EGD) framework that transfers institutional road safety expertise into a compact vision‑language model for visual road safety auditing. The method calibrates a teacher model against authoritative field audits, achieving a Cohen’s kappa of 0.74 before generating structured supervision for an 8‑billion‑parameter student model via Low‑Rank Adaptation. The authors also release Bangladesh Road Safety Audit (BD‑ARSA), an open dataset of 21,947 image‑audit records, and demonstrate that the student model outperforms both its larger teacher and Gemini‑2.5‑Flash in ordinal risk assessment and expert evaluation.
The paper introduces MEMENTO, a memory‑enhanced neural solver that improves routing problem solutions by using online data from repeated attempts to adjust action distributions during inference. It targets NP‑hard routing tasks such as the Traveling Salesman and Capacitated Vehicle Routing problems, outperforming existing tree‑search and policy‑gradient fine‑tuning methods. MEMENTO demonstrates strong scalability and data efficiency, achieving state‑of‑the‑art results on 11 of 12 evaluated tasks and enabling zero‑shot integration with diversity‑based solvers.
arXiv:2507.09924v2 Announce Type: replace-cross Abstract: Continually updating model-based indexes in generative retrieval with new documents remains challenging, as full retraining is computationall...
arXiv:2608.22301v1 Announce Type: cross Abstract: Humans imitate at the level of intent: given a demonstration, we infer its goal and carry it out with whatever tools, objects, and layouts are at han...
arXiv:2608.22341v1 Announce Type: cross Abstract: Lifting 3D hand poses from 2D monocular representations remains challenging due to the limited availability of large-scale, diverse 3D-annotated hand...
arXiv:2506.07356v3 Announce Type: replace Abstract: While Finetuning-as-a-Service (FaaS) enables customization of Large Language Models (LLMs) using user data, this service is vulnerable to safety de...