arXiv:2505.12299v4 Announce Type: replace-cross Abstract: The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks. However, the scarcity of diverse CoaT trajectories limits the expressiveness and generalization ability of such agents. While self-training is commonly employed to address data scarcity, existing approaches either […]
Deep Reinforcement Learning and The Tale of Two Temporal Difference Errors
arXiv:2603.21921v1 Announce Type: cross Abstract: The temporal difference (TD) error was first formalized in Sutton (1988), where it was first characterized as the difference between temporally successive predictions, and later, in that same work, formulated as the difference between a bootstrapped target and a prediction. Since then, these two interpretations of the TD error have […]
On Arbitrary Predictions from Equally Valid Models
arXiv:2507.19408v2 Announce Type: replace-cross Abstract: Model multiplicity refers to the existence of multiple machine learning models that describe the data equally well but may produce different predictions on individual samples. In medicine, these models can admit conflicting predictions for the same patient — a risk that is poorly understood and insufficiently addressed. In this study, […]
LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs
arXiv:2603.20293v1 Announce Type: new Abstract: Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these graphs often assume that the distributions of training and testing data are consistent. This assumption leads to significant […]
Learning to Interpret Weight Differences in Language Models
arXiv:2510.05092v4 Announce Type: replace-cross Abstract: Finetuning (pretrained) language models is a standard approach for updating their internal parametric knowledge and specializing them to new tasks and domains. However, the corresponding model weight changes (“weight diffs”) are not generally interpretable. While inspecting the finetuning dataset can give a sense of how the model might have changed, […]
PA3: Policy-Aware Agent Alignment through Chain-of-Thought
arXiv:2603.14602v2 Announce Type: replace-cross Abstract: Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all policies for every query introduces high latency and wastes compute. Furthermore, these lengthy prompts lead to long contexts, […]
A Stitch in Time: Learning Procedural Workflow via Self-Supervised Plackett-Luce Ranking
arXiv:2511.17805v2 Announce Type: replace-cross Abstract: Procedural activities, ranging from routine cooking to complex surgical operations, are highly structured sequences of actions performed in a specific temporal order. Despite the success of current self-supervised learning (SSL) methods on static images and short clips, these models often overlook the underlying sequential structure of such activities. We expose […]
From Causal Discovery to Dynamic Causal Inference in Neural Time Series
arXiv:2603.20980v1 Announce Type: cross Abstract: Time-varying causal models provide a powerful framework for studying dynamic scientific systems, yet most existing approaches assume that the underlying causal network is known a priori – an assumption rarely satisfied in real-world domains where causal structure is uncertain, evolving, or only indirectly observable. This limits the applicability of dynamic […]
Decoupling Numerical and Structural Parameters: An Empirical Study on Adaptive Genetic Algorithms via Deep Reinforcement Learning for the Large-Scale TSP
arXiv:2603.20702v1 Announce Type: cross Abstract: Proper parameter configuration is a prerequisite for the success of Evolutionary Algorithms (EAs). While various adaptive strategies have been proposed, it remains an open question whether all control dimensions contribute equally to algorithmic scalability. To investigate this, we categorize control variables into numerical parameters (e.g., crossover and mutation rates) and […]
RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for Rubric Generation
arXiv:2603.20882v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly evaluated and sometimes trained using automated graders such as LLM-as-judges that output scalar scores or preferences. While convenient, these approaches are often opaque: a single score rarely explains why an answer is good or bad, which requirements were missed, or how a system should […]
Detecting Neurovascular Instability from Multimodal Physiological Signals Using Wearable-Compatible Edge AI: A Responsible Computational Framework
arXiv:2603.20442v1 Announce Type: cross Abstract: We propose Melaguard, a multimodal ML framework (Transformer-lite, 1.2M parameters, 4-head self-attention) for detecting neurovascular instability (NVI) from wearable-compatible physiological signals prior to structural stroke pathology. The model fuses heart rate variability (HRV), peripheral perfusion index, SpO2, and bilateral phase coherence into a composite NVI Score, designed for edge inference […]
An InSAR Phase Unwrapping Framework for Large-scale and Complex Events
arXiv:2603.21378v1 Announce Type: cross Abstract: Phase unwrapping remains a critical and challenging problem in InSAR processing, particularly in scenarios involving complex deformation patterns. In earthquake-related deformation, shallow sources can generate surface-breaking faults and abrupt displacement discontinuities, which severely disrupt phase continuity and often cause conventional unwrapping algorithms to fail. Another limitation of existing learning-based unwrapping […]