LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks. However, progress is limited by the lack of high-coverage, long-horizon interaction trajectories collected from element-rich and rapidly evolving apps.
Foundation models such as Segment Anything Model 2 (SAM2) have transformed natural-image and video segmentation, and recent work has begun adapting them to medical imaging. These adaptations, however, are largely general-purpose models that treat MRI as one modality among many; large-scale, MRI-specific modelling and benchmarking remain limited, even though MRI's low soft-tissue contrast leaves many boundaries effectively invisible on individual slices.
Large language models achieve strong reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\leq 4 \, \mathrm{B}$ parameters) trained under limited budgets. We introduce MADA-RL, a post-training framework that specializes compact models into generator and critic roles and trains them with a debate-aware learning signal, fine-tuning only a small subset of parameters via LoRA adapters.
Class Incremental Learning (CIL) aims to learn new concepts consistently from a data stream without forgetting. Unlike typical CIL methods which need to learn a model from scratch, pre-trained model (PTM) can easily adapt to a new task with fine-tuning.
Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups. Most training-free methods, however, rank these units independently, implicitly treating the loss from pruning a set as the sum of its individual losses.
Developers frequently write uninformative git commit messages such as "fix" or "update stuff", degrading the value of version-control history for code review, debugging, and onboarding. We present CommitLLM, a three-stage pipeline that generates concise, Conventional Commits-compliant messages from code diffs using a fine-tuned small language model.
arXiv:2607. 15880v1 Announce Type: cross Abstract: Imitation Learning aims to learn skills from extensive observations and demonstrations for robots, so it suffers from data scarcity and environment generalization.
arXiv:2607. 15928v1 Announce Type: new Abstract: Adult and pediatric electrocardiogram (ECG) interpretation relies on age-sensitive criteria, and models pretrained mainly on adult ECGs often transfer poorly to pediatric populations when pediatric labels are scarce.
arXiv:2607. 16097v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the pretraining that precedes it.
arXiv:2607. 16053v1 Announce Type: cross Abstract: Gene regulatory networks (GRNs) link transcription factor (TF) proteins to their target genes, yet reconstructing these networks from genome-wide data remains challenging under practical and methodological constraints.
arXiv:2607. 16090v1 Announce Type: cross Abstract: Transferring policies across domains poses a vital challenge in reinforcement learning, due to the dynamics mismatch between the source and target domains.
arXiv:2607. 15380v1 Announce Type: cross Abstract: Electronic health records combine free-text clinical narratives with structured measurements such as vital signs, laboratory values, and comorbidities.
arXiv:2512. 00319v3 Announce Type: replace Abstract: The Structure Gap between probabilistic LLM generation and deterministic schema requirements hinders automated workflows.
arXiv:2605. 31289v2 Announce Type: replace-cross Abstract: Representation learning is a powerful tool for spatio-temporal abstraction within reinforcement learning (RL).
arXiv:2412. 10665v3 Announce Type: replace-cross Abstract: We introduce a foundation model for event classification in high-energy physics, built on a Graph Neural Network architecture and trained on 120 million simulated proton-proton collision events spanning 12 distinct physics processes.
arXiv:2607. 16122v1 Announce Type: new Abstract: Evaluations should do more than measure a models current performance.
arXiv:2607. 15414v1 Announce Type: cross Abstract: Large Language Models (LLMs) have emerged as powerful tools for processing the heterogeneous information environments of modern financial markets.
arXiv:2607. 15299v1 Announce Type: cross Abstract: In this paper, we propose MLLM-DataEngine, a novel closed-loop system that bridges data generation, model training, and evaluation.
arXiv:2607. 15687v1 Announce Type: new Abstract: Multimodal-attributed graphs (MAGs), whose nodes carry modalities such as images and text alongside topological structure, now pervade applications including social platforms, e-commerce, and biomedical networks, offering richer semantic signals than single-modality graphs.
arXiv:2607. 16031v1 Announce Type: cross Abstract: Data-driven pre-fault dynamic security assessment (DSA) rapidly evaluates the dynamic risk of credible contingencies on a power system using machine learning.