arXiv:2603.29328v3 Announce Type: replace-cross Abstract: Backdoor attacks on federated learning (FL) are most often evaluated with synthetic corner patches or out-of-distribution (OOD) patterns that are unlikely to arise in practice. In this paper, we revisit the backdoor threat to standard FL (a single global model) under a more realistic setting where triggers must be semantically […]
Multiscale Physics-Informed Neural Network for Complex Fluid Flows with Long-Range Dependencies
arXiv:2604.05652v1 Announce Type: cross Abstract: Fluid flows are governed by the nonlinear Navier-Stokes equations, which can manifest multiscale dynamics even from predictable initial conditions. Predicting such phenomena remains a formidable challenge in scientific machine learning, particularly regarding convergence speed, data requirements, and solution accuracy. In complex fluid flows, these challenges are exacerbated by long-range spatial […]
Evaluating Learner Representations for Differentiation Prior to Instructional Outcomes
arXiv:2604.05848v1 Announce Type: cross Abstract: Learner representations play a central role in educational AI systems, yet it is often unclear whether they preserve meaningful differences between students when instructional outcomes are unavailable or highly context-dependent. This work examines how to evaluate learner representations based on whether they retain separation between learners under a shared comparison […]
Graph-PiT: Enhancing Structural Coherence in Part-Based Image Synthesis via Graph Priors
arXiv:2604.06074v1 Announce Type: cross Abstract: Achieving fine-grained and structurally sound controllability is a cornerstone of advanced visual generation. Existing part-based frameworks treat user-provided parts as an unordered set and therefore ignore their intrinsic spatial and semantic relationships, which often results in compositions that lack structural integrity. To bridge this gap, we propose Graph-PiT, a framework […]
The two-clock problem in population dynamics
arXiv:2504.20388v2 Announce Type: replace Abstract: Biological time can be measured in two ways: in generations and in physical (chronological) time. When generations overlap, these two notions diverge, which impedes our ability to relate mathematical models to real populations. In this paper we show that nevertheless, the two clocks can be synchronised in the long run […]
Robust AI Security and Alignment: A Sisyphean Endeavor?
arXiv:2512.10100v2 Announce Type: replace Abstract: This manuscript establishes information-theoretic limitations for robustness of AI security and alignment by extending G”odel’s incompleteness theorem to AI. Knowing these limitations and preparing for the challenges they bring is critically important for the responsible adoption of the AI technology. Practical approaches to dealing with these challenges are provided as […]
Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models
arXiv:2407.14971v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain highly vulnerable to imperceptible adversarial perturbations, which can severely degrade both robustness and semantic quality in multimodal reasoning. In this […]
Synthesis of discrete-continuous quantum circuits with multimodal diffusion models
arXiv:2506.01666v3 Announce Type: replace-cross Abstract: Efficiently compiling quantum operations remains a major bottleneck in scaling quantum computing. Today’s state-of-the-art methods achieve low compilation error by combining search algorithms with gradient-based parameter optimization, but they incur long runtimes and require multiple calls to quantum hardware or expensive classical simulations, making their scaling prohibitive. Recently, machine-learning models […]
Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning
arXiv:2510.13909v2 Announce Type: replace-cross Abstract: Inductive Knowledge Graph Reasoning (KGR) aims to discover facts in open-domain KGs containing unknown entities and relations, which poses a challenge for KGR models in comprehending uncertain KG components. Existing studies have proposed Knowledge Graph Foundation Models (KGFMs) that learn structural invariances across KGs to handle this uncertainty. Recently, Large […]
Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs
arXiv:2601.09365v2 Announce Type: replace-cross Abstract: Common ground plays a critical role in situated spoken dialogs, where interlocutors must establish and maintain shared references to entities, events, and relations to sustain coherent interaction in a shared space and over time. With the increasing presence of embodied conversational agents and social robots, the ability to correctly ground […]
Not All Latent Spaces Are Flat: Hyperbolic Concept Control
arXiv:2603.14093v3 Announce Type: replace-cross Abstract: As modern text-to-image (T2I) models draw closer to synthesizing highly realistic content, the threat of unsafe content generation grows, and it becomes paramount to exercise control. Existing approaches steer these models by applying Euclidean adjustments to text embeddings, redirecting the generation away from unsafe concepts. In this work, we introduce […]
Geometric Limits of Knowledge Distillation: A Minimum-Width Theorem via Superposition Theory
arXiv:2604.04037v2 Announce Type: replace-cross Abstract: Knowledge distillation compresses large teachers into smaller students, but performance saturates at a loss floor that persists across training methods and objectives. We argue this floor is geometric: neural networks represent far more features than dimensions through superposition, and a student of width $d_S$ can encode at most $d_S cdot […]