arXiv:2604.00251v1 Announce Type: cross Abstract: In cases of prevalent diseases and disorders, such as Prenatal Alcohol Exposure (PAE), multi-site data collection allows for increased study samples. However, multi-site studies introduce additional variability through heterogeneous collection materials, such as scanner and acquisition protocols, which confound with biologically relevant signals. Neuroscientists often utilize statistical methods on image-derived […]
Asymmetric Actor-Critic for Multi-turn LLM Agents
arXiv:2604.00304v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong reasoning and conversational abilities, but ensuring reliable behavior in multi-turn interactions remains challenging. In many real-world applications, agents must succeed in one-shot settings where retries are impossible. Existing approaches either rely on reflection or post-hoc evaluation, which require additional attempts, or assume fully trainable […]
Go Big or Go Home: Simulating Mobbing Behavior with Braitenbergian Robots
arXiv:2604.00350v1 Announce Type: cross Abstract: We used the Webots robotics simulation platform to simulate a dyadic avoiding and mobbing predator behavior in a group of Braitenbergian robots. Mobbing is an antipredator adaptation used by some animals in which the individuals cooperatively attack or harass a predator to protect themselves. One way of coordinating a mobbing […]
Improving Generalization of Deep Learning for Brain Metastases Segmentation Across Institutions
arXiv:2604.00397v1 Announce Type: cross Abstract: Background: Deep learning has demonstrated significant potential for automated brain metastases (BM) segmentation; however, models trained at a singular institution often exhibit suboptimal performance at various sites due to disparities in scanner hardware, imaging protocols, and patient demographics. The goal of this work is to create a domain adaptation framework […]
Polysemanticity or Polysemy? Lexical Identity Confounds Superposition Metrics
arXiv:2604.00443v1 Announce Type: cross Abstract: If the same neuron activates for both “lender” and “riverside,” standard metrics attribute the overlap to superposition–the neuron must be compressing two unrelated concepts. This work explores how much of the overlap is due a lexical confound: neurons fire for a shared word form (such as “bank”) rather than for […]
Executing as You Generate: Hiding Execution Latency in LLM Code Generation
arXiv:2604.00491v1 Announce Type: cross Abstract: Current LLM-based coding agents follow a serial execution paradigm: the model first generates the complete code, then invokes an interpreter to execute it. This sequential workflow leaves the executor idle during generation and the generator idle during execution, resulting in unnecessary end-to-end latency. We observe that, unlike human developers, LLMs […]
Large Language Models for Variant-Centric Functional Evidence Mining
arXiv:2604.00075v1 Announce Type: new Abstract: Functional evidence is essential for clinical interpretation of genomic variants, but identifying relevant studies and translating experimental results into structured evidence remains labor intensive. We developed a benchmark based on ClinGen curated annotations to evaluate two large language models (LLMs), a non reasoning model (gpt-4o-mini) and a reasoning model (o4-mini), […]
Multimodal Analysis of State-Funded News Coverage of the Israel-Hamas War on YouTube Shorts
arXiv:2604.00994v1 Announce Type: cross Abstract: YouTube Shorts have become central to news consumption on the platform, yet research on how geopolitical events are represented in this format remains limited. To address this gap, we present a multimodal pipeline that combines automatic transcription, aspect-based sentiment analysis (ABSA), and semantic scene classification. The pipeline is first assessed […]
Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
arXiv:2509.21743v2 Announce Type: replace Abstract: Large reasoning models improve accuracy by producing long reasoning traces, but this inflates latency and cost, motivating inference-time efficiency. We propose Retrieval-of-Thought (RoT), which reuses prior reasoning as composable “thought” steps to guide new problems. RoT organizes steps into a thought graph with sequential and semantic edges to enable fast […]
SCoOP: Semantic Consistent Opinion Pooling for Uncertainty Quantification in Multiple Vision-Language Model Systems
arXiv:2603.23853v2 Announce Type: replace Abstract: Combining multiple Vision-Language Models (VLMs) can enhance multimodal reasoning and robustness, but aggregating heterogeneous models’ outputs amplifies uncertainty and increases the risk of hallucinations. We propose SCoOP (Semantic-Consistent Opinion Pooling), a training-free uncertainty quantification (UQ) framework for multi-VLM systems through uncertainty-weighted linear opinion pooling. The core idea is to treat […]
Adversarial Attacks in AI-Driven RAN Slicing: SLA Violations and Recovery
arXiv:2604.01049v1 Announce Type: cross Abstract: Next-generation (NextG) cellular networks are designed to support emerging applications with diverse data rate and latency requirements, such as immersive multimedia services and large-scale Internet of Things deployments. A key enabling mechanism is radio access network (RAN) slicing, which dynamically partitions radio resources into virtual resource blocks to efficiently serve […]
Neuro-Symbolic Process Anomaly Detection
arXiv:2603.26461v2 Announce Type: replace-cross Abstract: Process anomaly detection is an important application of process mining for identifying deviations from the normal behavior of a process. Neural network-based methods have recently been applied to this task, learning directly from event logs without requiring a predefined process model. However, since anomaly detection is a purely statistical task, […]