arXiv:2602.15195v3 Announce Type: replace-cross Abstract: LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging Face Hub citephuggingface_hub_docs, making them vulnerable to backdoor attacks. Current detection methods require running the model with test input data — making them impractical for screening thousands of adapters where […]
Eigen-Value: Efficient Domain-Robust Data Valuation via Eigenvalue-Based Approach
arXiv:2510.23409v3 Announce Type: replace-cross Abstract: Data valuation has become central in the era of data-centric AI. It drives efficient training pipelines and enables objective pricing in data markets by assigning a numeric value to each data point. Most existing data valuation methods estimate the effect of removing individual data points by evaluating changes in model […]
ALTO: Adaptive LoRA Tuning and Orchestration for Heterogeneous LoRA Training Workloads
arXiv:2604.05426v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) is now the dominant method for parameter-efficient fine-tuning of large language models, but achieving a high-quality adapter often requires systematic hyperparameter tuning because LoRA performance is highly sensitive to configuration choices. In practice, this leads to many concurrent LoRA jobs, often spanning heterogeneous tasks in multi-tenant environments. […]
Why Can’t I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
arXiv:2601.16211v2 Announce Type: replace-cross Abstract: Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of previously observed primitives. In this work, we tackle a key failure mode: models predict verbs via object-driven shortcuts (i.e., relying on the labeled object class) rather than temporal evidence. We argue that sparse compositional supervision and verb-object learning […]
Implementing Grassroots Logic Programs with Multiagent Transition Systems and AI
arXiv:2602.06934v3 Announce Type: replace-cross Abstract: Grassroots Logic Programs (GLP) is a multiagent, concurrent, logic programming language designed for the implementation of smartphone-based, serverless, grassroots platforms. Here, we start from GLP and maGLP — concurrent and multiagent abstract nondeterministic operational semantics for GLP, respectively — and from them derive dGLP and madGLP — implementation-ready deterministic operational […]
Moral Mazes in the Era of LLMs
arXiv:2603.20231v2 Announce Type: replace-cross Abstract: Navigating complex social situations is an integral part of corporate life, ranging from giving critical feedback without hurting morale to rejecting requests without alienating teammates. Although large language models (LLMs) are permeating the workplace, it is unclear how well they can navigate these norms. To investigate this question, we created […]
A graph based advection framework for climate-driven species distribution
arXiv:2604.05423v1 Announce Type: cross Abstract: Climate change is reshaping species interactions and movement across fragmented landscapes. Despite this, most mathematical models assume random diffusion, overlooking the influence of directed movement. Here, we develop a graph based reaction-diffusion-advection framework explicitly incorporating directional movement induced by environmental gradients. Our results show while diffusion promotes overall population persistence […]
Incident-Guided Spatiotemporal Traffic Forecasting
arXiv:2602.02528v2 Announce Type: replace-cross Abstract: Recent years have witnessed the rapid development of deep-learning-based, graph-neural-network-based forecasting methods for modern intelligent transportation systems. However, most existing work focuses exclusively on capturing spatio-temporal dependencies from historical traffic data, while overlooking the fact that suddenly occurring transportation incidents, such as traffic accidents and adverse weather, serve as external […]
Evaluation of Randomization through Style Transfer for Enhanced Domain Generalization
arXiv:2604.05616v1 Announce Type: cross Abstract: Deep learning models for computer vision often suffer from poor generalization when deployed in real-world settings, especially when trained on synthetic data due to the well-known Sim2Real gap. Despite the growing popularity of style transfer as a data augmentation strategy for domain generalization, the literature contains unresolved contradictions regarding three […]
Pursuit of biomarkers of brain diseases: Beyond cohort comparisons
arXiv:2509.10547v2 Announce Type: replace Abstract: Despite the diversity and volume of brain data acquired and advanced AI-based algorithms to analyze them, brain features are rarely used in clinics for diagnosis and prognosis. Here we argue that the field continues to rely on cohort comparisons to seek biomarkers, despite the well-established degeneracy of brain features. Using […]
Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion
arXiv:2604.05688v1 Announce Type: cross Abstract: Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention (SWA) can alleviate this bound, but integrating them into existing models remains difficult. Prior methods impose fine-grained structural requirements on both […]
Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning
arXiv:2604.05931v1 Announce Type: cross Abstract: Zero-shot unsupervised reinforcement learning (URL) offers a promising direction for building generalist agents capable of generalizing to unseen tasks without additional supervision. Among existing approaches, successor representations (SR) have emerged as a prominent paradigm due to their effectiveness in structured, low-dimensional settings. However, SR methods struggle to scale to high-dimensional […]