arXiv:2510.08768v1 Announce Type: new Abstract: Reinforcement learning (RL) policies often fail to generalize to new robots, tasks, or environments with different physical parameters, a challenge that limits their real-world applicability. This paper presents a simple, zero-shot transfer method based on…
arXiv:2510.09259v1 Announce Type: cross Abstract: Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance. While detection…
arXiv:2510.08774v1 Announce Type: new Abstract: Text embeddings from Large Language Models (LLMs) have become foundational for numerous applications. However, these models typically operate on raw text, overlooking the rich structural information, such as hyperlinks or citations, that provides crucial context…
arXiv:2510.09338v1 Announce Type: cross Abstract: We present a novel framework for training large language models with continuously adjustable internal representations that span the full spectrum from localist (interpretable, rule-based) to distributed (generalizable, efficient) encodings. The key innovation is a locality…
arXiv:2510.08779v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents often struggle in sparse-reward environments where traditional exploration strategies fail to discover effective action sequences. Large Language Models (LLMs) possess procedural knowledge and reasoning capabilities from text pretraining that could guide…
arXiv:2510.09472v1 Announce Type: cross Abstract: Despite the remarkable progress in neural models, their ability to generalize, a cornerstone for applications like logical reasoning, remains a critical challenge. We delineate two fundamental aspects of this ability: compositionality, the capacity to abstract…
arXiv:2510.08780v1 Announce Type: new Abstract: Neural network-based function approximation plays a pivotal role in the advancement of scientific computing and machine learning. Yet, training such models faces several challenges: (i) each target function often requires training a new model from…
arXiv:2505.14551v2 Announce Type: replace-cross Abstract: We investigate how a blockchain can distill the collective belief of its nodes regarding the trustworthiness of a (sub)set of nodes into a {em reputation system} that reflects the probability of correctly performing a task.…
arXiv:2506.03355v2 Announce Type: replace Abstract: Adversarial input attacks can cause a significant shift of CLIP embeddings. This can affect the downstream robustness of models incorporating CLIP in the pipeline, such as text-to-image generative models or large vision language models. While…
arXiv:2311.01591v4 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have achieved state-of-the-art results in many relevant tasks where decisions might disproportionately impact specific communities. However, existing work on fair GNNs often assumes that either sensitive attributes are fully observed or…
