arXiv:2604.01029v1 Announce Type: cross Abstract: Multi-LLM revision pipelines, in which a second model reviews and improves a draft produced by a first, are widely assumed to derive their gains from genuine error correction. We question this assumption with a controlled decomposition experiment that uses four matched conditions to separate second-pass gains into three additive components: […]
Collaborative AI Agents and Critics for Fault Detection and Cause Analysis in Network Telemetry
arXiv:2604.00319v1 Announce Type: new Abstract: We develop algorithms for collaborative control of AI agents and critics in a multi-actor, multi-critic federated multi-agent system. Each AI agent and critic has access to classical machine learning or generative AI foundation models. The AI agents and critics collaborate with a central server to complete multimodal tasks such as […]
Screening Is Enough
arXiv:2604.01178v1 Announce Type: cross Abstract: A core limitation of standard softmax attention is that it does not define a notion of absolute query–key relevance: attention weights are obtained by redistributing a fixed unit mass across all keys according to their relative scores. As a result, relevance is defined only relative to competing keys, and irrelevant […]
Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning
arXiv:2603.09697v2 Announce Type: replace-cross Abstract: Recent advances in spectral optimization, notably Muon, have demonstrated that constraining update steps to the Stiefel manifold can significantly accelerate training and improve generalization. However, Muon implicitly assumes an isotropic optimization landscape, enforcing a uniform spectral update norm across all eigen-directions. We argue that this “egalitarian” constraint is suboptimal for […]
Towards Automatic Soccer Commentary Generation with Knowledge-Enhanced Visual Reasoning
arXiv:2604.00057v1 Announce Type: cross Abstract: Soccer commentary plays a crucial role in enhancing the soccer game viewing experience for audiences. Previous studies in automatic soccer commentary generation typically adopt an end-to-end method to generate anonymous live text commentary. Such generated commentary is insufficient in the context of real-world live televised commentary, as it contains anonymous […]
The data heat island effect: quantifying the impact of AI data centers in a warming world
arXiv:2603.20897v2 Announce Type: replace-cross Abstract: The strong and continuous increase of AI-based services leads to the steady proliferation of AI data centres worldwide with the unavoidable escalation of their power consumption. It is unknown how this energy demand for computational purposes will impact the surrounding environment. Here, we focus our attention on the heat dissipation […]
On the Non-Identifiability of Steering Vectors in Large Language Models
arXiv:2602.06801v4 Announce Type: replace-cross Abstract: Activation steering methods are widely used to control large language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpretation assumes that steering directions are identifiable and uniquely recoverable from input-output behavior. We show that, under white-box single-layer access, steering vectors are fundamentally non-identifiable due to […]
Unified Architecture Metamodel of Information Systems Developed by Generative AI
arXiv:2604.00171v1 Announce Type: cross Abstract: The rapid development of AI and LLMs has driven new methods of SDLC, in which a large portion of code, technical, and business documentation is generated automatically. However, since there is no single architectural framework that can provide consistent, repeatable transformations across different representation layers of information systems, such systems […]
RAGShield: Provenance-Verified Defense-in-Depth Against Knowledge Base Poisoning in Government Retrieval-Augmented Generation Systems
arXiv:2604.00387v1 Announce Type: cross Abstract: RAG systems deployed across federal agencies for citizen-facing services are vulnerable to knowledge base poisoning attacks, where adversaries inject malicious documents to manipulate outputs. Recent work demonstrates that as few as 10 adversarial passages can achieve 98.2% retrieval success rates. We observe that RAG knowledge base poisoning is structurally analogous […]
UCell: rethinking generalizability and scaling of bio-medical vision models
arXiv:2604.00243v1 Announce Type: cross Abstract: The modern deep learning field is a scale-centric one. Larger models have been shown to consistently perform better than smaller models of similar architecture. In many sub-domains of biomedical research, however, the model scaling is bottlenecked by the amount of available training data, and the high cost associated with generating […]
The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment
arXiv:2604.00279v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the modality gap. This gap limits tasks requiring cross-modal interchangeability, such as captioning and joint clustering. Existing post-processing approaches can partially improve cross-modal compatibility; however, […]
Hierarchical Pre-Training of Vision Encoders with Large Language Models
arXiv:2604.00086v1 Announce Type: cross Abstract: The field of computer vision has experienced significant advancements through scalable vision encoders and multimodal pre-training frameworks. However, existing approaches often treat vision encoders and large language models (LLMs) as independent modules, limiting the integration of hierarchical visual features. In this work, we propose HIVE (Hierarchical Pre-Training of Vision Encoders), […]