arXiv:2604.14455v1 Announce Type: new Abstract: AI models underpin modern intelligent systems, driving advances across science, medicine, finance, and technology. Yet developing high-performing AI models remains a labor-intensive process that requires expert practitioners to iteratively design architectures, engineer representations, implement training pipelines and refine approaches through empirical evaluation. Existing AutoML methods partially alleviate this burden but […]
Explainable Graph Neural Networks for Interbank Contagion Surveillance: A Regulatory-Aligned Framework for the U.S. Banking Sector
arXiv:2604.14232v1 Announce Type: cross Abstract: The Spatial-Temporal Graph Attention Network (ST-GAT) framework was created to serve as an explainable GNN-based solution for detecting bank distress early warning signs and for conducting macro-prudential surveillance of the interbank system in the United States. The ST-GAT framework models 8,103 FDIC insured institutions across 58 quarterly snapshots (2010Q1-2024Q2). Bilateral […]
Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Training
arXiv:2408.14728v2 Announce Type: replace-cross Abstract: Adversarial training has proven effective in improving the robustness of deep neural networks against adversarial attacks. However, this enhanced robustness often comes at the cost of a substantial drop in accuracy on clean data. In this paper, we address this limitation by introducing Tangent Direction Guided Adversarial Training (TART), a […]
Evaluation of Agents under Simulated AI Marketplace Dynamics
arXiv:2604.14256v1 Announce Type: cross Abstract: Modern information access ecosystems consist of mixtures of systems, such as retrieval systems and large language models, and increasingly rely on marketplaces to mediate access to models, tools, and data, making competition between systems inherent to deployment. In such settings, outcomes are shaped not only by benchmark quality but also […]
Improving Human Performance with Value-Aware Interventions: A Case Study in Chess
arXiv:2604.14465v1 Announce Type: new Abstract: AI systems are increasingly used to assist humans in sequential decision-making tasks, yet determining when and how an AI assistant should intervene remains a fundamental challenge. A potential baseline is to recommend the optimal action according to a strong model. However, such actions assume optimal follow-up actions, which human decision […]
Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
arXiv:2604.14267v1 Announce Type: cross Abstract: Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavailable during pretraining. While reinforcement learning has been widely adopted for training such agents, existing approaches face key limitations: process supervision often suffers from unstable value estimation, whereas outcome supervision struggles […]
DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
arXiv:2509.03472v2 Announce Type: replace-cross Abstract: Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to train neural networks. During training, converting model weights and activations into low-precision formats, i.e., quantization, can drastically reduce training times, energy consumption, and cost, and is thus a widely used […]
Aerial Multi-Functional RIS in Fluid Antennas-Aided Full-Duplex Networks: A Self-Optimized Hybrid Deep Reinforcement Learning Approach
arXiv:2604.14309v1 Announce Type: cross Abstract: To address high data traffic demands of sixth-generation (6G) networks, this paper proposes a novel architecture that integrates autonomous aerial vehicles (AAVs) and multi-functional reconfigurable intelligent surfaces (MF-RISs) as AM-RIS in fluid antenna (FA)-assisted full-duplex (FD) networks. The AM-RIS provides hybrid functionalities, including signal reflection, amplification, and energy harvesting (EH), […]
Response-Aware User Memory Selection for LLM Personalization
arXiv:2604.14473v1 Announce Type: new Abstract: A common approach to personalization in large language models (LLMs) is to incorporate a subset of the user memory into the prompt at inference time to guide the model’s generation. Existing methods select these subsets primarily using similarity between user memory items and input queries, ignoring how features actually affect […]
Thermodynamic Diffusion Inference with Minimal Digital Conditioning
arXiv:2604.14332v1 Announce Type: cross Abstract: Diffusion-model inference and overdamped Langevin dynamics are formally identical. A physical substrate that encodes the score function therefore equilibrates to the correct output by thermodynamics alone, requiring no digital arithmetic during inference and potentially achieving a $10,000times$ reduction in energy relative to a GPU. Two fundamental barriers have until now […]
Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion
arXiv:2511.14178v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have demonstrated significant potential in real-world robotic manipulation. However, pre-trained VLA policies still suffer from substantial performance degradation during downstream deployment. Although fine-tuning can mitigate this issue, its reliance on costly demonstration collection and intensive computation makes it impractical in real-world settings. In this work, we introduce […]
The Cost of Language: Centroid Erasure Exposes and Exploits Modal Competition in Multimodal Language Models
arXiv:2604.14363v1 Announce Type: cross Abstract: Multimodal language models systematically underperform on visual perception tasks, yet the structure underlying this failure remains poorly understood. We propose centroid replacement, collapsing each token to its nearest K-means centroid, as a controlled probe for modal dependence. Across seven models spanning three architecture families, erasing text centroid structure costs 4$times$ […]