2787 papers
This paper advances Deep Equilibrium Models by establishing a fixed point theory that relaxes the restrictive strict-contraction requirement, proving existence and uniqueness under Wardowski -contractions, demonstrating convergence of Krasnoselskii–Mann iteration for nonexpansive operators, and deriving Lipschitz stability bounds for robust training.
This paper proposes a defense framework combining adversarial training and gradient masking to significantly enhance the robustness of deep learning-based intrusion detection systems against adversarial attacks while maintaining high accuracy on benign traffic.
This paper proposes a unified soft-adaptive aggregation framework that mitigates sequence and depth information dilution in long-context LLMs by introducing Soft-ChunkAttn for differentiable semantic chunking and Virtual Dynamic Block-AttnRes for input-adaptive layer merging, all while preserving the original computation graph for efficient GPU deployment.
This paper introduces EIDOLON-RL, a hybrid hierarchical reinforcement learning framework that integrates opponent modeling, world modeling, and risk-adaptive planning to generate fair, legible, and computationally efficient AI characters for AAA action games by mathematically enforcing production constraints like animation validity and intentional imperfection rather than treating them as post-hoc engineering fixes.
This paper demonstrates that optimizing physical neural networks with control-aware objectives, which prioritize preserving candidate-action rankings over static regression accuracy, significantly enhances closed-loop regulation performance and robustness against perturbations in tasks like homeostatic regulation and Cart-Pole stabilization.
This paper establishes a verified taxonomy and unified benchmark for deep learning-based anomaly detection in dynamic graphs, revealing that simple degree-based heuristics often outperform complex deep models on synthetic benchmarks while failing on real-world data, and exposing critical flaws in current evaluation practices and published implementations.
This paper introduces X-StrGNN, a zero-degradation post-hoc explanation layer for the StrGNN graph anomaly detector that provides stable, low-cost structural and temporal attributions for flagged edges while preserving the original model's detection performance to machine precision.
This paper introduces a post-hoc explainability framework that enhances the high-performing TADDY anomaly detector for dynamic social graphs by generating dual spatial and temporal Shapley attributions to identify influential neighbors and historical snapshots, achieving high fidelity and sufficiency metrics without compromising detection accuracy.
This paper introduces a framework for semi-supervised anomaly detection on dynamic graphs that provides exact, closed-form deviation attribution and learns an amortised event mask to explain decisions with zero impact on detection performance, while revealing that alerts often stem equally from individual node behavior and population baseline shifts.
This paper presents CitationGuard, a multi-evidence framework that combines Isolation Forest anomaly detection with weighted evidence fusion to generate a Hybrid Suspicion Score for prioritizing bibliographic records requiring verification in digital libraries.