Zero-Day Vulnerabilities in Enterprise AI Systems: Legal and Technical Implications
The discovery of critical zero-day vulnerabilities in widely deployed AI systems raises urgent questions about cybersecurity liability and disclosure obligations.
Tokenization, Fusion and Decoupling: Bridging the Granularity Mismatch Between Large Language Models and Knowledge Graphs
arXiv:2602.22698v1 Announce Type: new Abstract: Leveraging Large Language Models (LLMs) for Knowledge Graph Completion (KGC) is promising but hindered by a fundamental granularity mismatch. LLMs operate on fragmented token sequences, whereas entities are the fundamental units in knowledge graphs (KGs)...
Probing for Knowledge Attribution in Large Language Models
arXiv:2602.22787v1 Announce Type: new Abstract: Large language models (LLMs) often generate fluent but unfounded claims, or hallucinations, which fall into two types: (i) faithfulness violations - misusing user context - and (ii) factuality violations - errors from internal knowledge. Proper...
Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching
arXiv:2602.22871v1 Announce Type: new Abstract: Reasoning with large language models often benefits from generating multiple chains-of-thought, but existing aggregation strategies are typically trajectory-level (e.g., selecting the best trace or voting on the final answer), discarding useful intermediate work from partial...
MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations
arXiv:2602.23184v1 Announce Type: new Abstract: We present MTRAG-UN, a benchmark for exploring open challenges in multi-turn retrieval augmented generation, a popular use of large language models. We release a benchmark of 666 tasks containing over 2,800 conversation turns across 6...
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
arXiv:2602.23197v1 Announce Type: new Abstract: Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations. In practice, such models are often fine-tuned to improve zero-shot performance on downstream tasks, allowing them to solve...
SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables
arXiv:2602.23286v1 Announce Type: new Abstract: Real-world Table-Text question answering (QA) tasks require models that can reason across long text and source tables, traversing multiple hops and executing complex operations such as aggregation. Yet existing benchmarks are small, manually curated -...
Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function
arXiv:2602.22255v1 Announce Type: new Abstract: We introduce a sequence modeling framework in which the latent state is a complex-valued wave function evolving on a finite-dimensional Hilbert space under a learned, time-dependent Hamiltonian. Unlike standard recurrent architectures that rely on gating...
Sustainable LLM Inference using Context-Aware Model Switching
arXiv:2602.22261v1 Announce Type: new Abstract: Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference strategy where...
AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
arXiv:2602.22268v1 Announce Type: new Abstract: Quantization followed by parameter-efficient fine-tuning has emerged as a promising paradigm for downstream adaptation under tight GPU memory constraints. However, this sequential pipeline fails to leverage the intricate interaction between quantization bit-width and LoRA rank....
Support Tokens, Stability Margins, and a New Foundation for Robust LLMs
arXiv:2602.22271v1 Announce Type: new Abstract: Self-attention is usually described as a flexible, content-adaptive way to mix a token with information from its past. We re-interpret causal self-attention transformers, the backbone of modern foundation models, within a probabilistic framework, much like...
Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathy
arXiv:2602.22288v1 Announce Type: new Abstract: Sudden cardiac death (SCD) is unpredictable, and its prediction in Chagas cardiomyopathy (CC) remains a significant challenge, especially in patients not classified as high risk. While AI and machine learning models improve risk stratification, their...
Global River Forecasting with a Topology-Informed AI Foundation Model
arXiv:2602.22293v1 Announce Type: new Abstract: River systems operate as inherently interconnected continuous networks, meaning river hydrodynamic simulation ought to be a systemic process. However, widespread hydrology data scarcity often restricts data-driven forecasting to isolated predictions. To achieve systemic simulation and...
AviaSafe: A Physics-Informed Data-Driven Model for Aviation Safety-Critical Cloud Forecasts
arXiv:2602.22298v1 Announce Type: new Abstract: Current AI weather forecasting models predict conventional atmospheric variables but cannot distinguish between cloud microphysical species critical for aviation safety. We introduce AviaSafe, a hierarchical, physics-informed neural forecaster that produces global, six-hourly predictions of these...
Training Agents to Self-Report Misbehavior
arXiv:2602.22303v1 Announce Type: new Abstract: Frontier AI agents may pursue hidden goals while concealing their pursuit from oversight. Alignment training aims to prevent such behavior by reinforcing the correct goals, but alignment may not always succeed and can lead to...
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...
Learning geometry-dependent lead-field operators for forward ECG modeling
arXiv:2602.22367v1 Announce Type: new Abstract: Modern forward electrocardiogram (ECG) computational models rely on an accurate representation of the torso domain. The lead-field method enables fast ECG simulations while preserving full geometric fidelity. Achieving high anatomical accuracy in torso representation is,...
Calibrated Test-Time Guidance for Bayesian Inference
arXiv:2602.22428v1 Announce Type: new Abstract: Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existing approaches, however, focus on maximizing reward rather than sampling from the true Bayesian posterior, leading...
ECHO: Encoding Communities via High-order Operators
arXiv:2602.22446v1 Announce Type: new Abstract: Community detection in attributed networks faces a fundamental divide: topological algorithms ignore semantic features, while Graph Neural Networks (GNNs) encounter devastating computational bottlenecks. Specifically, GNNs suffer from a Semantic Wall of feature over smoothing in...
Persistent Nonnegative Matrix Factorization via Multi-Scale Graph Regularization
arXiv:2602.22536v1 Announce Type: new Abstract: Matrix factorization techniques, especially Nonnegative Matrix Factorization (NMF), have been widely used for dimensionality reduction and interpretable data representation. However, existing NMF-based methods are inherently single-scale and fail to capture the evolution of connectivity structures...
Justices appear dubious of challenge to constitutionality of foreclosure sales
The argument yesterday in Pung v Isabella County had two distinct threads. On the one hand, the justices who discussed the question presented seemed to have no doubt that they […]The postJustices appear dubious of challenge to constitutionality of foreclosure...
How strong is New York's "illegal gambling" case against Valve's loot boxes?
Lawyers tell Ars the state has a tough road ahead, even as Valve is uniquely vulnerable.
Last 24 hours to get TechCrunch Disrupt 2026 tickets at the lowest rates of the year
The lowest rates of the year for TechCrunch Disrupt 2026 end after today. Prices go up at 11:59 p.m. PT. Don't miss connecting with 10,000 founders, investors, and operators, and key takeaways from 250+ industry leaders. Register now to save...
Breakthrough in Quantum-Resistant Cryptography: Preparing for the Post-Quantum Era
NIST has finalized post-quantum cryptography standards, but the transition to quantum-resistant systems presents immense technical and organizational challenges.
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
arXiv:2602.21420v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become the leading paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard RLVR algorithms suffer from a well-documented pathology: while they improve Pass@1 accuracy through sharpened...
ECHOSAT: Estimating Canopy Height Over Space And Time
arXiv:2602.21421v1 Announce Type: cross Abstract: Forest monitoring is critical for climate change mitigation. However, existing global tree height maps provide only static snapshots and do not capture temporal forest dynamics, which are essential for accurate carbon accounting. We introduce ECHOSAT,...
Disaster Question Answering with LoRA Efficiency and Accurate End Position
arXiv:2602.21212v1 Announce Type: new Abstract: Natural disasters such as earthquakes, torrential rainfall, floods, and volcanic eruptions occur with extremely low frequency and affect limited geographic areas. When individuals face disaster situations, they often experience confusion and lack the domain-specific knowledge...
Structured Prompt Language: Declarative Context Management for LLMs
arXiv:2602.21257v1 Announce Type: new Abstract: We present SPL (Structured Prompt Language), a declarative SQL-inspired language that treats large language models as generative knowledge bases and their context windows as constrained resources. SPL provides explicit WITH BUDGET/LIMIT token management, an automatic...
Under the Influence: Quantifying Persuasion and Vigilance in Large Language Models
arXiv:2602.21262v1 Announce Type: new Abstract: With increasing integration of Large Language Models (LLMs) into areas of high-stakes human decision-making, it is important to understand the risks they introduce as advisors. To be useful advisors, LLMs must sift through large amounts...
ToolMATH: A Math Tool Benchmark for Realistic Long-Horizon Multi-Tool Reasoning
arXiv:2602.21265v1 Announce Type: new Abstract: We introduce \ToolMATH, a math-grounded benchmark that evaluates tool-augmented language models in realistic multi-tool environments where the output depends on calling schema-specified tools and sustaining multi-step execution. It turns math problems into a controlled, correctness-checkable...