arXiv:2605.11232v1 Announce Type: new Abstract: Fraud detection and anti-money-laundering (AML) compliance are high-value domains for large language models (LLMs), but their serving requirements differ sharply from generic chat workloads. Compliance prompts are often prefix-heavy, schema-constrained, and evidence-rich, combining reusable policy instructions, risk taxonomies, transaction or document context, and short structured outputs such as JSON labels […]
Quantifying Rodda and Graham Gait Classification from 3D Makerless Kinematics derived from a Single-view Video in a Heterogeneous Pediatric Clinical Cohort
arXiv:2605.11314v1 Announce Type: cross Abstract: Cerebral Palsy (CP) is a neurological disorder of movement and the most common cause of lifelong physical disability in childhood. Approximately 75% of children with CP are ambulatory, and accurate gait assessment is central to preserving walking function, which deteriorates by mid-adulthood in a quarter to half of adults with […]
Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
arXiv:2602.02007v4 Announce Type: replace-cross Abstract: Standard Retrieval Augmented Generation (RAG) is poorly matched to agent memory. Unlike large heterogeneous corpora, agent memory forms a bounded and coherent interaction stream in which many spans are highly correlated or near duplicates. As a result, flat top-$k$ similarity retrieval often returns redundant context, while summary-centric hierarchies can blur […]
Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence
arXiv:2605.11348v1 Announce Type: cross Abstract: During disasters, extracting causal relations from social media can strengthen situational awareness by identifying factors linked to casualties, physical damage, infrastructure disruption, and cascading impacts. However, disaster-related posts are often informal, fragmented, and context-dependent, and they may describe personal experiences rather than explicit causal relations. In this work, we examine […]
The Semantic Training Gap: Ontology-Grounded Tool Architectures for Industrial AI Agent Systems
arXiv:2605.11234v1 Announce Type: new Abstract: Large language model (LLM)-based AI agents are increasingly deployed in manufacturing environments for analytics, quality management, and decision support. These agents demonstrate statistical fluency with domain terminology but lack grounded understanding of operational semantics — the relational structure that connects equipment identifiers, process parameters, failure codes, and regulatory constraints within […]
Spatial Adapter: Structured Spatial Decomposition and Closed-Form Covariance for Frozen Predictors
arXiv:2605.11394v1 Announce Type: cross Abstract: We present the Spatial Adapter, a parameter-efficient post-hoc layer that equips any frozen first-stage predictor with a structured spatial representation of its residual field and an induced closed-form spatial covariance. The adapter operates as a cascade second stage on residuals, jointly learning a spatially regularized orthonormal basis and per-sample scores […]
DWDP: Distributed Weight Data Parallelism for High-Performance LLM Inference on NVL72
arXiv:2604.01621v2 Announce Type: replace-cross Abstract: Large language model (LLM) inference increasingly depends on multi-GPU execution, yet existing inference parallelization strategies require layer-wise inter-rank synchronization, making end-to-end performance sensitive to workload imbalance. We present DWDP (Distributed Weight Data Parallelism), an inference parallelization strategy that preserves data-parallel execution while offloading MoE weights across peer GPUs and fetching […]
Deep Minds and Shallow Probes
arXiv:2605.11448v1 Announce Type: cross Abstract: Neural representations are not unique objects. Even when two systems realize the same downstream computation, their hidden coordinates may differ by reparameterization. A probe family intended to reveal structure already present in a representation should therefore be stable under the relevant representation symmetries rather than be tied to a particular […]
Unlocking LLM Creativity in Science through Analogical Reasoning
arXiv:2605.11258v1 Announce Type: new Abstract: Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that can consistently generate novel and diverse solutions to open-ended problems. We evaluate LLMs on the task of open-ended solution generation and quantify their tendency to mode collapse into low-diversity generations. To […]
Decaf: Improving Neural Decompilation with Automatic Feedback and Search
arXiv:2605.11501v1 Announce Type: cross Abstract: Decompilers are useful tools used in reverse engineering to understand compiled source code. Reconstructing source code from compiled binaries is a challenging task, because high-level syntax, identifiers, and custom data types are generally lost as the compiler translates human-readable code to low-level machine code. Deterministic decompilers are useful tools for […]
Matching Meaning at Scale: Evaluating Semantic Search for 18th-Century Intellectual History through the Case of Locke
arXiv:2605.09236v2 Announce Type: replace-cross Abstract: While digitized corpora have transformed the study of intellectual transmission, current methods rely heavily on lexical text reuse detection, capturing verbatim quotations but fundamentally missing paraphrases and complex implicit engagement. This paper evaluates semantic search in 18th-century intellectual history through the reception of John Locke’s foundational work. Using expert annotation […]
Three Regimes of Context-Parametric Conflict: A Predictive Framework and Empirical Validation
arXiv:2605.11574v1 Announce Type: cross Abstract: The literature on how large language models handle conflict between their training knowledge and a contradicting document presents a persistent empirical contradiction: some studies find models stubbornly retain their trained answers, ignoring provided documents nearly half the time, while others find models readily defer to the document, following context approximately […]