Fine-tuning and adaptation

Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning

arXiv:2606. 25700v1 Announce Type: new Abstract: When fine-tuning Large Language Models (LLMs), there has been success in minimizing both memory usage and computation with Parameter-Efficient Fine-Tuning (PEFT), like Low Rank Adaptation (LoRA).

Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

arXiv:2606. 24952v1 Announce Type: cross Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it.

Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

arXiv:2606. 26002v1 Announce Type: new Abstract: We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks.

EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression

arXiv:2606. 25285v1 Announce Type: new Abstract: Post-Training Sparsity (PTS) has emerged as a crucial paradigm for compressing Large Language Models to facilitate efficient deployment on resource-constrained devices.

Supervised Reinforcement Learning for the Coordination of Distributed Energy Resources

arXiv:2606. 24947v1 Announce Type: new Abstract: The increasing integration of distributed energy resources (DERs) is crucial for power system decarbonization, yet unlocking DERs' flexibility is challenged by their inherent uncertainties and modelling complexity.

Digital Twin-Driven Adaptive Sim-to-Real Alignment via Reinforcement Learning for Vibration-Based Bearing Health Monitoring Under Data Scarcity

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.

From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE Control

arXiv:2502. 02205v4 Announce Type: replace Abstract: The application of deep learning for partial differential equation (PDE)-constrained control is gaining increasing attention.

Curvature-Guided Mixing for MLLM Adaptation

arXiv:2606. 24963v1 Announce Type: cross Abstract: Fine-tuning Multimodal Large Language Models (MLLMs) on specialized tasks often leads to catastrophic forgetting of their general capabilities.

GCT-MARL: Graph-Based Contrastive Transfer for Sample-Efficient Cooperative Multi-Agent Reinforcement Learning

arXiv:2606. 25073v1 Announce Type: new Abstract: In cooperative multi-agent reinforcement learning (MARL), from a deployment perspective, it is challenging and expensive to train agents from scratch for each new environment or task.

Improved Large Language Diffusion Models

arXiv:2606. 25331v1 Announce Type: cross Abstract: Modern large language models are predominantly trained with autoregressive factorization and causal attention.

TL++: Accuracy and Privacy Preserving Traversal Learning for Distributed Intelligent Systems

arXiv:2606. 25627v1 Announce Type: new Abstract: Distributed intelligent systems increasingly need to train across data silos without centralizing raw data.

Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection

arXiv:2606. 24985v1 Announce Type: new Abstract: Personalization in wearable-based stress detection remains challenging due to substantial inter-individual variability in physiological and behavioral responses.

Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning

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.

The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms

arXiv:2606. 25450v1 Announce Type: new Abstract: Traditional evaluations measure a learning algorithm's final performance on an i.

The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order

arXiv:2606. 24993v1 Announce Type: new Abstract: Sequential learning is order-dependent: from Pile-style next-token domain adaptation to instruction-SFT and DPO, N candidate sources induce N!

WinDOM: Self-Family Distillation for Small-Model GUI Grounding

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.

Multipath Adaptive Gated Bottleneck Latent ODE with Raman Data Fusion for Cell Culture Process Forecasting

Mammalian cell-culture processes underpin the manufacture of many biopharmaceuticals, yet keeping a run on track is hard: critical process parameters drift over days, and an off-specification trend is often confirmed too late to intervene. Early-stage, multi-day forecasts could enable timely adjustment of feeding, sampling, and control, but bioprocess forecasting is challenging because measurements are sparse and irregularly sampled, operating conditions are heterogeneous across cell lines and media, and runs with near-identical early behaviour can diverge into different futures.

The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar

Text detoxification, the automated detection and mitigation of abusive and harmful content, is essential for ensuring the safety of online communities and protecting users. However, low resource languages such as Tatar have received little research attention.

Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel

Enhancing Brain MRI Anomaly Detection and Reasoning with ROI Rethink and Synthetic Data

Medical vision-language models typically generate diagnoses through single-pass inference without indicating which image regions support their conclusions. This lack of spatial grounding limits clinical utility: outputs cannot be audited, and models may hallucinate findings on normal scans.