arXiv:2604.23888v1 Announce Type: cross Abstract: Adaptation of blackbox generative models has been widely studied recently through the exploration of several methods including generator fine-tuning, latent space searches, leveraging singular value decomposition, and so on. However, adapting large-scale generative AI tools to specific use cases continues to be challenging, as many of these industry-grade models are […]
StoryTR: Narrative-Centric Video Temporal Retrieval with Theory of Mind Reasoning
arXiv:2604.23198v1 Announce Type: new Abstract: Current video moment retrieval excels at action-centric tasks but struggles with narrative content. Models can see textitwhat is happening but fail to reason textitwhy it matters. This semantic gap stems from the lack of textbfTheory of Mind (ToM): the cognitive ability to infer implicit intentions, mental states, and narrative causality […]
Progressive Approximation in Deep Residual Networks: Theory and Validation
arXiv:2604.24154v1 Announce Type: cross Abstract: The Universal Approximation Theorem (UAT) guarantees universal function approximation but does not explain how residual models distribute approximation across layers. We reframe residual networks as a layer-wise approximation process that builds an approximation trajectory from input to target, and prove the existence of progressive trajectories where error decreases monotonically with […]
Beyond Single-Agent Alignment: Preventing Context-Fragmented Violations in Multi-Agent Systems
arXiv:2604.22879v1 Announce Type: cross Abstract: We identify and formalize a novel security risk: Context-Fragmented Violations (CFVs) – a class of policy breaches where individual agent actions appear locally safe and reasonable, yet collectively violate organizational policies because critical policy facts are siloed in different departments private contexts. Existing prompt-based alignment mechanisms and monolithic interceptors are […]
AVISE: Framework for Evaluating the Security of AI Systems
arXiv:2604.20833v2 Announce Type: replace-cross Abstract: As artificial intelligence (AI) systems are increasingly deployed across critical domains, their security vulnerabilities pose growing risks of high-profile exploits and consequential system failures. Yet systematic approaches to evaluating AI security remain underdeveloped. In this paper, we introduce AVISE (AI Vulnerability Identification and Security Evaluation), a modular open-source framework for […]
AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting
arXiv:2604.23239v1 Announce Type: new Abstract: Accurate long-term time series forecasting (LTSF) requires the capture of complex long-range dependencies and dynamic periodic patterns. Recent advances in frequency-domain analysis offer a global perspective for uncovering temporal characteristics. However, real-world time series often exhibit pronounced cross-domain heterogeneity where variables that appear synchronized in the time domain can differ […]
Discovering Agentic Safety Specifications from 1-Bit Danger Signals
arXiv:2604.23210v1 Announce Type: new Abstract: Can large language model agents discover hidden safety objectives through experience alone? We introduce EPO-Safe (Experiential Prompt Optimization for Safe Agents), a framework where an LLM iteratively generates action plans, receives sparse binary danger warnings, and evolves a natural language behavioral specification through reflection. Unlike standard LLM reflection methods that […]
Citation-Driven Multi-View Training for Patent Embeddings: QaECTER and Sophia-Bench
arXiv:2604.22897v1 Announce Type: cross Abstract: Patent retrieval underpins critical decisions in innovation, examination, and IP strategy, yet progress has been hampered by the absence of benchmarks that reflect the diversity of real world search scenarios. We address this gap with two contributions. First, we introduce Sophiabench, a large-scale patent retrieval benchmark comprising 10,000 queries and […]
Progressive Approximation in Deep Residual Networks: Theory and Validation
arXiv:2604.24154v1 Announce Type: cross Abstract: The Universal Approximation Theorem (UAT) guarantees universal function approximation but does not explain how residual models distribute approximation across layers. We reframe residual networks as a layer-wise approximation process that builds an approximation trajectory from input to target, and prove the existence of progressive trajectories where error decreases monotonically with […]
Beyond Single-Agent Alignment: Preventing Context-Fragmented Violations in Multi-Agent Systems
arXiv:2604.22879v1 Announce Type: cross Abstract: We identify and formalize a novel security risk: Context-Fragmented Violations (CFVs) – a class of policy breaches where individual agent actions appear locally safe and reasonable, yet collectively violate organizational policies because critical policy facts are siloed in different departments private contexts. Existing prompt-based alignment mechanisms and monolithic interceptors are […]
Mean-Field and Pairwise Approaches for the SIRI Model on Poisson Networks
arXiv:2604.23243v1 Announce Type: new Abstract: Compartmental epidemic models, grounded in mass-action kinetics, often assume homogeneous mixing. Although this neglects network structure, recent results show that for Poisson random graphs, the classical SIR model, especially the susceptible decay curve, matches the susceptible decay dynamics of its network counterpart. Motivated by this, we investigate whether the extended […]
AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting
arXiv:2604.23239v1 Announce Type: new Abstract: Accurate long-term time series forecasting (LTSF) requires the capture of complex long-range dependencies and dynamic periodic patterns. Recent advances in frequency-domain analysis offer a global perspective for uncovering temporal characteristics. However, real-world time series often exhibit pronounced cross-domain heterogeneity where variables that appear synchronized in the time domain can differ […]