arXiv:2512.08965v1 Announce Type: new Abstract: Language Models (LMs) struggle with complex, interdependent instructions, particularly in high-stakes domains like finance where precision is critical. We introduce FIFE, a novel, high-difficulty benchmark designed to assess LM instruction-following capabilities for financial analysis tasks.…
arXiv:2505.15138v2 Announce Type: replace Abstract: This paper investigates infinite-horizon average reward Constrained Markov Decision Processes (CMDPs) with general parametrization. We propose a Primal-Dual Natural Actor-Critic algorithm that adeptly manages constraints while ensuring a high convergence rate. In particular, our algorithm…
arXiv:2512.08967v1 Announce Type: new Abstract: Recent advancements in Large Language Models (LLMs) have led to their widespread adoption in daily applications. Despite their impressive capabilities, they remain vulnerable to adversarial attacks, as even minor meaning-preserving changes such as synonym substitutions…
arXiv:2509.24125v3 Announce Type: replace Abstract: In this technical note, we study the problem of inverse permutation learning in decoder-only transformers. Given a permutation and a string to which that permutation has been applied, the model is tasked with producing the…
arXiv:2512.08968v1 Announce Type: new Abstract: The rapid scaling of large computational models has led to a critical increase in energy and compute costs. Inspired by biological systems where structure and function emerge from low-energy configurations, we introduce StructuredDNA, a sparse…
arXiv:2512.06357v2 Announce Type: replace Abstract: Multi-step time-series prediction is an essential supportive step for decision-makers in several industrial areas. Artificial intelligence techniques, which use a neural network component in various forms, have recently frequently been used to accomplish this step.…
arXiv:2512.08969v1 Announce Type: new Abstract: We propose the Uncertainty Contrastive Framework (UCF), a Positive-Unlabeled (PU) representation learning framework that integrates uncertainty-aware contrastive loss, adaptive temperature scaling, and a self-attention-guided LSTM encoder to improve classification under noisy and imbalanced conditions. UCF…
arXiv:2106.05426v5 Announce Type: replace-cross Abstract: How related are the representations learned by neural language models, translation models, and language tagging tasks? We answer this question by adapting an encoder-decoder transfer learning method from computer vision to investigate the structure among…
arXiv:2512.08976v1 Announce Type: new Abstract: We introduce Contrastive Region Masking (CRM), a training free diagnostic that reveals how multimodal large language models (MLLMs) depend on specific visual regions at each step of chain-of-thought (CoT) reasoning. Unlike prior approaches limited to…
arXiv:2509.06796v2 Announce Type: replace-cross Abstract: A Membership Inference Attack (MIA) assesses how much a target machine learning model reveals about its training data by determining whether specific query instances were part of the training set. State-of-the-art MIAs rely on training…
