arXiv:2604.00186v1 Announce Type: cross Abstract: This paper extends the Acemoglu-Restrepo task exposure framework to address the labor market effects of agentic artificial intelligence systems: autonomous AI agents capable of completing entire occupational workflows rather than discrete tasks. Unlike prior automation technologies that substitute for individual subtasks, agentic AI systems execute end-to-end workflows involving multi-step reasoning, […]
First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models
arXiv:2604.00455v1 Announce Type: cross Abstract: Recent Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across various multimodal tasks that require understanding both visual and linguistic inputs. However, object hallucination — the generation of nonexistent objects in answers — remains a persistent challenge. Although several approaches such as retraining and external grounding methods have been proposed […]
Toward Optimal Sampling Rate Selection and Unbiased Classification for Precise Animal Activity Recognition
arXiv:2604.00517v1 Announce Type: cross Abstract: With the rapid advancements in deep learning techniques, wearable sensor-aided animal activity recognition (AAR) has demonstrated promising performance, thereby improving livestock management efficiency as well as animal health and welfare monitoring. However, existing research often prioritizes overall performance, overlooking the fact that classification accuracies for specific animal behavioral categories may […]
Empirical Validation of the Classification-Verification Dichotomy for AI Safety Gates
arXiv:2604.00072v1 Announce Type: cross Abstract: Can classifier-based safety gates maintain reliable oversight as AI systems improve over hundreds of iterations? We provide comprehensive empirical evidence that they cannot. On a self-improving neural controller (d=240), eighteen classifier configurations — spanning MLPs, SVMs, random forests, k-NN, Bayesian classifiers, and deep networks — all fail the dual conditions […]
Diversity-Aware Reverse Kullback-Leibler Divergence for Large Language Model Distillation
arXiv:2604.00223v1 Announce Type: cross Abstract: Reverse Kullback-Leibler (RKL) divergence has recently emerged as the preferred objective for large language model (LLM) distillation, consistently outperforming forward KL (FKL), particularly in regimes with large vocabularies and significant teacher-student capacity mismatch, where RKL focuses learning on dominant modes rather than enforcing dense alignment. However, RKL introduces a structural […]
Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewards
arXiv:2604.00258v1 Announce Type: cross Abstract: While apprenticeship learning has shown promise for inducing effective pedagogical policies directly from student interactions in e-learning environments, most existing approaches rely on optimal or near-optimal expert demonstrations under a fixed reward. Real-world student interactions, however, are often inherently imperfect and evolving: students explore, make errors, revise strategies, and refine […]
Robust Multimodal Safety via Conditional Decoding
arXiv:2604.00310v1 Announce Type: cross Abstract: Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions. Models aligned on text alone show a higher rate of successful attacks when extended to two or more modalities. In this work, we propose a simple conditional decoding strategy, CASA (Classification Augmented with Safety Attention) […]
COTTA: Context-Aware Transfer Adaptation for Trajectory Prediction in Autonomous Driving
arXiv:2604.00402v1 Announce Type: cross Abstract: Developing robust models to accurately predict the trajectories of surrounding agents is fundamental to autonomous driving safety. However, most public datasets, such as the Waymo Open Motion Dataset and Argoverse, are collected in Western road environments and do not reflect the unique traffic patterns, infrastructure, and driving behaviors of other […]
A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation
arXiv:2604.00493v1 Announce Type: cross Abstract: Chest X-rays (CXRs) are among the most frequently performed imaging examinations worldwide, yet rising imaging volumes increase radiologist workload and the risk of diagnostic errors. Although artificial intelligence (AI) systems have shown promise for CXR interpretation, most generate only final predictions, without making explicit how visual evidence is translated into […]
Perspective: Towards sustainable exploration of chemical spaces with machine learning
arXiv:2604.00069v1 Announce Type: cross Abstract: Artificial intelligence is transforming molecular and materials science, but its growing computational and data demands raise critical sustainability challenges. In this Perspective, we examine resource considerations across the AI-driven discovery pipeline–from quantum-mechanical (QM) data generation and model training to automated, self-driving research workflows–building on discussions from the “SusML workshop: Towards […]
Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation
arXiv:2604.00131v1 Announce Type: cross Abstract: Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues. In contrast, memory-augmented LLM agents rely on “always-on” retrieval and “flat” memory storage, causing high interference and latency as histories grow. We introduce Oblivion, a memory control framework that […]
Making Sense of AI Agents Hype: Adoption, Architectures, and Takeaways from Practitioners
arXiv:2604.00189v1 Announce Type: cross Abstract: To support practitioners in understanding how agentic systems are designed in real-world industrial practice, we present a review of practitioner conference talks on AI agents. We analyzed 138 recorded talks to examine how companies adopt agent-based architectures (Objective 1), identify recurring architectural strategies and patterns (Objective 2), and analyze application […]