Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2607. 03887v1 Announce Type: cross Abstract: The increasing complexity and frequency of software vulnerabilities demand efficient methods to analyze and prioritize threats.
arXiv:2607. 03487v1 Announce Type: cross Abstract: Mutual information (MI) estimation is a central problem in machine learning and statistics; however, existing benchmarks typically evaluate estimators on simplified, low-dimensional distributions, leaving their performance on complex, realistic data largely unexplored.
arXiv:2403. 11199v2 Announce Type: replace-cross Abstract: Unitarity is a useful principle for stabilizing deep neural networks, but in graph neural networks (GNNs) instability is induced not only by learnable parameters but also by the graph propagation operator.
arXiv:2607. 02703v1 Announce Type: cross Abstract: In this paper, we describe LLMoxie, an institutional AI platform whose three-tiered architecture supports multi-cloud and on-premise inference, a LiteLLM/MLflow control plane for authentication, budgeting, PII masking, and observability, and an application augmentation layer for AI coding agents.
arXiv:2607. 03981v1 Announce Type: cross Abstract: Memes have become influential communication tools on social media, combining viral visuals with concise messaging to convey impactful ideas.
arXiv:2607. 04409v1 Announce Type: new Abstract: Learning and planning in imagination using world models provides an effective paradigm for training agents for decision-making.
arXiv:2607. 05365v1 Announce Type: cross Abstract: Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech.
arXiv:2607. 04978v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs) underpin a growing family of latent world models for control from raw pixels, but every existing JEPA world model commits at training time to a single inference paradigm: either trajectory optimisation in a learned dynamics model, or direct behaviour cloning.
arXiv:2602. 14401v2 Announce Type: replace-cross Abstract: Vision-Language Navigation VLN requires large-scale trajectory instruction data from private indoor environments, raising significant privacy concerns.
arXiv:2604. 03329v2 Announce Type: replace-cross Abstract: Automatic violence detection from video is challenging because violent interactions may be distant, occluded, or only partially visible.
arXiv:2607. 04091v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have achieved remarkable performance in graph representation learning, yet their inherent vulnerability to adversarial attacks poses severe security risks.
arXiv:2607. 04729v1 Announce Type: cross Abstract: LLM agents are increasingly applied to vulnerability analysis, but existing benchmarks have not kept pace.
arXiv:2408. 13378v5 Announce Type: replace Abstract: Workflows in drug-target interaction (DTI) assessment require integrating heterogeneous data from predictive models, curated resources, and observations from experimental literature.
arXiv:2603. 18528v2 Announce Type: replace Abstract: Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge.
arXiv:2607. 04977v1 Announce Type: new Abstract: Accurately estimating the unknown target label distribution is the critical first step for adapting to label shift.
arXiv:2510. 14007v2 Announce Type: replace-cross Abstract: We introduce Conditional Clifford-Steerable CNNs (C-CSCNNs), a unified framework that incorporates equivariance to arbitrary pseudo-Euclidean groups and significantly improves the expressivity of standard CSCNNs.
arXiv:2607. 05001v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated analysis and reasoning.
arXiv:2607. 02746v1 Announce Type: cross Abstract: Machine learning has shown speedups for numerical methods in physics applications, but integrating Python-based libraries into high-performance C++ solvers creates performance bottlenecks.
arXiv:2607. 03870v1 Announce Type: new Abstract: As LLMs generate increasingly long outputs, effective uncertainty estimation must identify errors at fine-grained levels rather than discard entire responses.
arXiv:2607. 02338v2 Announce Type: replace-cross Abstract: Hierarchical Navigable Small World (HNSW) graphs serve as the industry standard due to their logarithmic complexity and strong empirical performance.