arXiv:2602.10152v2 Announce Type: replace Abstract: Saliency maps are increasingly used as design guidance in siRNA efficacy prediction, yet attribution methods are rarely validated before motivating sequence edits. We introduce a pre-synthesis gate: a protocol for counterfactual sensitivity faithfulness that tests whether mutating high-saliency positions changes model output more than composition-matched controls. Cross-dataset transfer reveals two […]
Iterative Quantum Feature Maps
arXiv:2506.19461v3 Announce Type: replace-cross Abstract: Quantum machine learning models that leverage quantum circuits as quantum feature maps (QFMs) are recognized for their enhanced expressive power in learning tasks. Such models have demonstrated rigorous end-to-end quantum speedups for specific families of classification problems. However, deploying deep QFMs on real quantum hardware remains challenging due to circuit […]
A Cognitive Explainer for Fetal ultrasound images classifier Based on Medical Concepts
arXiv:2201.07798v4 Announce Type: replace-cross Abstract: Fetal standard scan plane detection during 2-D mid-pregnancy examinations is a highly complex task, which requires extensive medical knowledge and years of training. Although deep neural networks (DNN) can assist inexperienced operators in these tasks, their lack of transparency and interpretability limit their application. Despite some researchers have been committed […]
Algorithmic Collusion by Large Language Models
arXiv:2404.00806v5 Announce Type: replace-cross Abstract: We conduct experiments with algorithmic pricing agents based on Large Language Models (LLMs). In oligopoly settings, LLM-based pricing agents quickly and autonomously reach supracompetitive prices and profits. Variation in seemingly innocuous phrases in LLM instructions (“prompts”) substantially influence the degree of supracompetitive pricing. We develop novel techniques for behavioral analysis […]
Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
arXiv:2502.05151v3 Announce Type: replace-cross Abstract: With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. An emerging ecosystem of models and tools aims to support researchers throughout the scientific lifecycle, including (1) searching for relevant literature, (2) generating research ideas and conducting experiments, (3) producing text-based […]
Aligning Compound AI Systems via System-level DPO
arXiv:2502.17721v4 Announce Type: replace-cross Abstract: Compound AI systems, comprising multiple interacting components such as LLMs, foundation models, and external tools, have demonstrated remarkable improvements compared to single models in various tasks. To ensure their effective deployment in real-world applications, aligning these systems with human preferences is crucial. However, aligning the compound system via policy optimization, […]
The Malicious Technical Ecosystem: Exposing Limitations in Technical Governance of AI-Generated Non-Consensual Intimate Images of Adults
arXiv:2504.17663v2 Announce Type: replace-cross Abstract: In this paper, we adopt a survivor-centered approach to locate and dissect the role of sociotechnical AI governance in preventing AI-Generated Non-Consensual Intimate Images (AIG-NCII) of adults, colloquially known as “deep fake pornography.” We identify a “malicious technical ecosystem” or “MTE,” comprising of open-source face-swapping models and nearly 200 “nudifying” […]
Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents
arXiv:2603.05517v1 Announce Type: cross Abstract: Autonomous LLM agents fail because long-horizon policy remains implicit in model weights and transcripts, while safety is retrofitted post hoc. We propose Traversal-as-Policy: distill sandboxed OpenHands execution logs into a single executable Gated Behavior Tree (GBT) and treat tree traversal — rather than unconstrained generation — as the control policy […]
Causal Interpretation of Neural Network Computations with Contribution Decomposition
arXiv:2603.06557v1 Announce Type: cross Abstract: Understanding how neural networks transform inputs into outputs is crucial for interpreting and manipulating their behavior. Most existing approaches analyze internal representations by identifying hidden-layer activation patterns correlated with human-interpretable concepts. Here we take a direct approach to examine how hidden neurons act to drive network outputs. We introduce CODEC […]
vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models
arXiv:2603.04444v2 Announce Type: replace-cross Abstract: As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing — selecting the right model for each query at inference time — has become a critical systems challenge. We present vLLM Semantic Router, a signal-driven decision routing framework for Mixture-of-Modality (MoM) model […]
The Compute ICE-AGE: Invariant Compute Envelope under Addressable Graph Evolution
arXiv:2602.16736v2 Announce Type: replace-cross Abstract: This paper presents empirical results from a production-grade C++ implementation of a deterministic semantic state substrate derived from prior formal work on Bounded Local Generator Classes (Martin, 2026). The system was mathematically specified prior to implementation and realized as a CPU-resident graph engine operating under bounded local state evolution. Contemporary […]
Reparameterized Tensor Ring Functional Decomposition for Multi-Dimensional Data Recovery
arXiv:2603.01034v2 Announce Type: replace-cross Abstract: Tensor Ring (TR) decomposition is a powerful tool for high-order data modeling, but is inherently restricted to discrete forms defined on fixed meshgrids. In this work, we propose a TR functional decomposition for both meshgrid and non-meshgrid data, where factors are parameterized by Implicit Neural Representations (INRs). However, optimizing this […]