A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Shriniket Dixit, Anant Kumar, Kathiravan Srinivasan, et al.
This review explores AI's contributions to improving CRISPR-based genome editing, addressing challenges like off-target effects and delivery, and discussing future research directions.
Tianyu Wu, Shizhu He, Jingping Liu, et al.
This paper provides a concise overview of ChatGPT's history, core techniques, pros and cons, and potential future development, serving as an entry point for understanding the model.
De Jong Yeong, Gustavo Velasco-Hernandez, John M. Barry, et al.
This paper provides an end-to-end review of sensor hardware, calibration, and fusion techniques for object detection in autonomous vehicles, highlighting challenges and future research directions.
Zhouyuan Ma, Yutao Wu, Hanxun Huang, et al.
HarmProfile is a content-centric benchmark dataset of over 80,000 validated harmful artifacts from 23 frontier LLMs, defining model-level risk profiles and revealing that harmfulness and diversity grow with model capability.
Alwin Peng, Julian Michael, Henry Sleight, et al.
Proposes rapid response defenses that block entire classes of LLM jailbreaks after observing only a few examples, achieving a 240x reduction in attack success rate.
Yuanhe Zhang, Weiliu Wang, Jie Ren, et al.
Proposes ILL, an inaudible red teaming method using low-frequency waveforms to attack LALMs, and DRG, a defense that detects distribution shifts and requests reacquisition, reducing accuracy by up to 67 points.
Asaf Yehudai, Lilach Eden, Alan Li, et al.
First comprehensive survey of evaluation methods for LLM-based agents, analyzing five perspectives and identifying gaps in cost-efficiency, safety, and robustness.
Saman Marandi, Yu-Shu Hu, Mohammad Modarres
This paper presents a framework for automated construction of Dynamic Master Logic models as knowledge graphs from technical documentation using retrieval-augmented large language models, validated on a nuclear reactor system.
Vatsal Baherwani, Tom Goldstein, Ashwinee Panda
This paper demonstrates that frontier language models can perform 'invisible reasoning' using semantically irrelevant filler tokens, improving accuracy by up to 13 percentage points and hiding objectives from CoT monitoring.
Aslı Durmuşoğlu, Şahin Yıldırım
This paper proposes a robust adaptive neuro-fuzzy inference system (RANFIS) for active landing-gear vibration control, achieving superior performance over MBNN and ANFIS in reducing vibration peaks, settling times, and steady-state errors.
Neha Yadav, Sagar Pande, Aditya Khamparia, et al.
This paper proposes a deep learning-based intrusion detection system for IoT networks in 5G environments, achieving 99.76% accuracy with an autoencoder model.
Yida Lu, Jiale Cheng, Zhexin Zhang, et al.
This paper introduces LongSafety, a benchmark and framework for evaluating the safety of large language models in long-context scenarios, revealing that safety risks increase with context length.