GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundar…

The paper proposes Jellyfish, a zero-shot federated unlearning scheme that effectively removes the influence of forgotten data from federated learning models while maintaining model utility and privac…

The paper proposes a novel Disentanglement-based Equivariant Learning (DEAL) framework that enhances compositional VQA by disentangling concepts and enforcing equivariant constraints, achieving state-…

GaMi is a multimodal material identification system that uses mmWave and acoustic sensing with a cross-modal subtractive disentanglement framework to achieve high accuracy (95.2%) for material identif…

The paper proposes Localized and Disentangled Knowledge Editing (LDKE), a framework that significantly improves knowledge editing in Multimodal Large Language Models by ensuring edits are both precise…

The paper proposes an inference-time activation steering framework, utilizing orthogonalization, to achieve fine-grained, deterministic control over discrete musical attributes like Pitch and Duration…

The authors introduce IVD-SSM, a model for narrative similarity that uses a hybrid State-Space Model and a Structurally Gated Alignment head to disentangle structural invariants from lexical variants.

The paper proposes explicitly disentangling positional and semantic representations in Transformer encoders, demonstrating that this separation allows for a clearer understanding of how positional inf…

The paper introduces QADR, a novel hybrid quantum-classical framework that efficiently trains variational quantum circuits by localizing entanglement reduction, thereby overcoming the exponential memo…

The paper proposes an engineering framework, inspired by metamaterials physics, to quantify institutional coordination and predict civilizational stability in the age of AI.

TriLens is a white-box detector that monitors the entropy of three internal streams (attention, feed-forward, residual) at every layer of a language model to detect hallucinations by tracking how inte…

The paper constructs a family of simple quantum states (pseudoentangled states) generated by constant-depth circuits that exhibit non-trivial entanglement structure, demonstrating that entanglement st…

The paper introduces a multi-surface evidence framework to provide comprehensive observability for post-quantum TLS migration, enabling robust measurement of session behavior and endpoint capabilities…

CoreUnlearn introduces a novel framework that disentangles and removes undesirable concepts from text-guided diffusion models by targeting specific, erasure-critical components of the concept embeddin…

The paper argues that traditional identity-based reputation mechanisms are structurally inapplicable to language model agents because their mutable, modular nature makes them ontologically dissociativ…

The paper demonstrates that cryptographically undetectable backdoors can be embedded into modern, state-of-the-art neural networks by exploiting inherent, latent geometric properties of the learned re…

This paper explores the constraints of achieving quantum advantage in circuit cutting while maintaining low overhead, classical hardness, and trainability, and introduces a two-block circuit family th…

The paper introduces CHARM, a novel framework that detects and mitigates cascading hallucination—the amplification of errors across multi-step agentic RAG pipelines—achieving an 82.1% reduction in err…