ROKA: Robust Knowledge Unlearning against Adversaries
arXiv:2603.00436v1 Announce Type: new Abstract: The need for machine unlearning is critical for data privacy, yet existing methods often cause Knowledge Contamination by unintentionally damaging related knowledge. Such a degraded model performance after unlearning has been recently leveraged for new...
Controllable Reasoning Models Are Private Thinkers
arXiv:2602.24210v1 Announce Type: new Abstract: AI agents powered by reasoning models require access to sensitive user data. However, their reasoning traces are difficult to control, which can result in the unintended leakage of private information to external parties. We propose...
Provable Subspace Identification of Nonlinear Multi-view CCA
arXiv:2602.23785v1 Announce Type: new Abstract: We investigate the identifiability of nonlinear Canonical Correlation Analysis (CCA) in a multi-view setup, where each view is generated by an unknown nonlinear map applied to a linear mixture of shared latents and view-private noise....
MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models
arXiv:2602.23798v1 Announce Type: new Abstract: Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. To address this dual non-disclosure constraint, we propose MPU,...
fEDM+: A Risk-Based Fuzzy Ethical Decision Making Framework with Principle-Level Explainability and Pluralistic Validation
arXiv:2602.21746v1 Announce Type: new Abstract: In a previous work, we introduced the fuzzy Ethical Decision-Making framework (fEDM), a risk-based ethical reasoning architecture grounded in fuzzy logic. The original model combined a fuzzy Ethical Risk Assessment module (fERA) with ethical decision...
Measuring Pragmatic Influence in Large Language Model Instructions
arXiv:2602.21223v1 Announce Type: cross Abstract: It is not only what we ask large language models (LLMs) to do that matters, but also how we prompt. Phrases like "This is urgent" or "As your supervisor" can shift model behavior without altering...
Make Every Draft Count: Hidden State based Speculative Decoding
arXiv:2602.21224v1 Announce Type: cross Abstract: Speculative decoding has emerged as a pivotal technique to accelerate LLM inference by employing a lightweight draft model to generate candidate tokens that are subsequently verified by the target model in parallel. However, while this...
Autonomous Vehicles and Liability: Who Is Responsible When AI Drives?
As autonomous vehicles approach widespread deployment, legal frameworks for determining liability in accidents involving self-driving cars remain uncertain.
ACAR: Adaptive Complexity Routing for Multi-Model Ensembles with Auditable Decision Traces
arXiv:2602.21231v1 Announce Type: cross Abstract: We present ACAR (Adaptive Complexity and Attribution Routing), a measurement framework for studying multi-model orchestration under auditable conditions. ACAR uses self-consistency variance (sigma) computed from N=3 probe samples to route tasks across single-model, two-model, and...
The Mean is the Mirage: Entropy-Adaptive Model Merging under Heterogeneous Domain Shifts in Medical Imaging
arXiv:2602.21372v1 Announce Type: cross Abstract: Model merging under unseen test-time distribution shifts often renders naive strategies, such as mean averaging unreliable. This challenge is especially acute in medical imaging, where models are fine-tuned locally at clinics on private data, producing...
Agentic AI for Intent-driven Optimization in Cell-free O-RAN
arXiv:2602.22539v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) is emerging as a key enabler for autonomous radio access networks (RANs), where multiple large language model (LLM)-based agents reason and collaborate to achieve operator-defined intents. The open RAN (O-RAN) architecture...
When Should an AI Act? A Human-Centered Model of Scene, Context, and Behavior for Agentic AI Design
arXiv:2602.22814v1 Announce Type: new Abstract: Agentic AI increasingly intervenes proactively by inferring users' situations from contextual data yet often fails for lack of principled judgment about when, why, and whether to act. We address this gap by proposing a conceptual...
Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
arXiv:2602.22983v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly used, their security risks have drawn increasing attention. Existing research reveals that LLMs are highly susceptible to jailbreak attacks, with effectiveness varying across language contexts. This paper investigates...
Bankruptcy as a National Security Risk lawreview - Minnesota Law Review
By JASON JIA-XI WU. Full Text. Defense contractors lie at the heart of the U.S. national security regime. Each year, over half of the federal defense budget is allocated to contracts outsourcing military operations, projects, and services to private companies....
The Crisis in U.S. Cancer Care: Law, Markets, and Privatization lawreview - Minnesota Law Review
By DANIEL G. AARON. Full Text. Cancer is surging among youth and young adults in the United States, yet, instead of public regulation addressing its root causes, we have outsourced the management of cancer to the private sector. A suite...
The Rise of AI-Powered Legal Research: Transforming How Lawyers Work
AI-powered legal research tools are fundamentally changing the practice of law, offering unprecedented efficiency while raising questions about quality and oversight.
CRISPR Gene Therapy Patents: The Legal Battle Reshaping Biotechnology
The ongoing patent disputes surrounding CRISPR gene editing technology have profound implications for biotech innovation, patient access, and IP strategy.
AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
arXiv:2602.22755v1 Announce Type: new Abstract: We introduce AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors. Each model has one of 14 concerning behaviors--such as sycophantic deference, opposition to AI regulation, or secret geopolitical...
Quantity Convergence, Quality Divergence: Disentangling Fluency and Accuracy in L2 Mandarin Prosody
arXiv:2602.23071v1 Announce Type: new Abstract: While second language (L2) learners may acquire target syntactic word order, mapping this syntax onto appropriate prosodic structures remains a persistent challenge. This study investigates the fossilization and stability of the L2 syntax-prosody interface by...
Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory
arXiv:2602.22345v1 Announce Type: new Abstract: This thesis addresses two persistent and closely related challenges in modern deep learning, reliability and efficiency, through a unified framework grounded in Spectral Geometry and Random Matrix Theory (RMT). As deep networks and large language...
Robust Long-Form Bangla Speech Processing: Automatic Speech Recognition and Speaker Diarization
arXiv:2602.21741v1 Announce Type: new Abstract: We describe our end-to-end system for Bengali long-form speech recognition (ASR) and speaker diarization submitted to the DL Sprint 4.0 competition on Kaggle. Bengali presents substantial challenges for both tasks: a large phoneme inventory, significant...
DLT-Corpus: A Large-Scale Text Collection for the Distributed Ledger Technology Domain
arXiv:2602.22045v1 Announce Type: new Abstract: We introduce DLT-Corpus, the largest domain-specific text collection for Distributed Ledger Technology (DLT) research to date: 2.98 billion tokens from 22.12 million documents spanning scientific literature (37,440 publications), United States Patent and Trademark Office (USPTO)...
Neural network optimization strategies and the topography of the loss landscape
arXiv:2602.21276v1 Announce Type: new Abstract: Neural networks are trained by optimizing multi-dimensional sets of fitting parameters on non-convex loss landscapes. Low-loss regions of the landscapes correspond to the parameter sets that perform well on the training data. A key issue...
On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation
arXiv:2602.21424v1 Announce Type: new Abstract: Reinforcement learning (RL) agents under partial observability often condition actions on internally accumulated information such as memory or inferred latent context. We formalise such information-conditioned interaction patterns as behavioural dependency: variation in action selection with...
Mamba Meets Scheduling: Learning to Solve Flexible Job Shop Scheduling with Efficient Sequence Modeling
arXiv:2602.21546v1 Announce Type: new Abstract: The Flexible Job Shop Problem (FJSP) is a well-studied combinatorial optimization problem with extensive applications for manufacturing and production scheduling. It involves assigning jobs to various machines to optimize criteria, such as minimizing total completion...
ABM-UDE: Developing Surrogates for Epidemic Agent-Based Models via Scientific Machine Learning
arXiv:2602.21588v1 Announce Type: new Abstract: Agent-based epidemic models (ABMs) encode behavioral and policy heterogeneity but are too slow for nightly hospital planning. We develop county-ready surrogates that learn directly from exascale ABM trajectories using Universal Differential Equations (UDEs): mechanistic SEIR-family...
HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders
arXiv:2602.21009v1 Announce Type: cross Abstract: Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints. While summarizing history via interest centers offers a practical alternative,...
Wasserstein Distributionally Robust Online Learning
arXiv:2602.20403v1 Announce Type: new Abstract: We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from a Wasserstein ambiguity set centered at past observations. While this paradigm is well understood in...
CGSTA: Cross-Scale Graph Contrast with Stability-Aware Alignment for Multivariate Time-Series Anomaly Detection
arXiv:2602.20468v1 Announce Type: new Abstract: Multivariate time-series anomaly detection is essential for reliable industrial control, telemetry, and service monitoring. However, the evolving inter-variable dependencies and inevitable noise render it challenging. Existing methods often use single-scale graphs or instance-level contrast. Moreover,...
Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models
arXiv:2602.19101v1 Announce Type: new Abstract: Value alignment of Large Language Models (LLMs) requires us to empirically measure these models' actual, acquired representation of value. Among the characteristics of value representation in humans is that they distinguish among value of different...