Understanding Annotator Safety Policy with Interpretability
arXiv:2605.05329v1 Announce Type: new Abstract: Safety policies define what constitutes safe and unsafe AI outputs, guiding data annotation and model…
Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
arXiv:2605.05097v2 Announce Type: replace-cross Abstract: LLMs are trained once, then deployed into a world that never stops changing. External memory…
Dynamic Pondering Sparsity-aware Mixture-of-Experts Transformer for Event Stream based Visual Object Tracking
arXiv:2605.06112v1 Announce Type: cross Abstract: Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as low illumination…
Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs
arXiv:2605.06111v1 Announce Type: cross Abstract: Reinforcement learning (RL) with verifiable rewards has proven effective at post-training LLMs for coding, yet…
Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search
arXiv:2605.04057v2 Announce Type: replace-cross Abstract: This paper focuses on a key challenge in Neural Architecture Search (NAS): integrating established architectural…
OracleProto: A Reproducible Framework for Benchmarking LLM Native Forecasting via Knowledge Cutoff and Temporal Masking
arXiv:2605.03762v1 Announce Type: new Abstract: Large language models are moving from static text generators toward real-world decision-support systems, where forecasting…
Self-Improvement for Fast, High-Quality Plan Generation
arXiv:2605.03625v1 Announce Type: new Abstract: Generative models trained on synthetic plan data are a promising approach to generalized planning. Recent…
Quantifying the human visual exposome with vision language models
arXiv:2605.03863v1 Announce Type: new Abstract: The visual environment is a fundamental yet unquantified determinant of mental health. While the concept…
Agentic-imodels: Evolving agentic interpretability tools via autoresearch
arXiv:2605.03808v1 Announce Type: new Abstract: Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and…
