A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Sarah Mohammed Alshehri, Sanaa Abdullah Sharaf, Rania Abdullrahman Molla
A systematic literature review of 28 studies (2020-2025) analyzing how graph neural networks are applied to detect cyberattacks in IoT, web, phishing, and network traffic domains.
P. Colombo, T. Pires, Malik Boudiaf, et al.
SaulLM-7B is a 7-billion-parameter LLM tailored for the legal domain, trained on over 30 billion tokens of English legal text and instruction-tuned to achieve state-of-the-art legal comprehension and generation.
Hanzhuo Tan, Qi Luo, Jing Li, et al.
LLM4Decompile is the first open-source LLM series trained to decompile binary code, outperforming GPT-4o and Ghidra by over 100% in re-executability.
W. Yeadon, Alex Peach, Craig P. Testrow
Evaluates ChatGPT variants on university-level physics coding assignments, finding students outperform AI and human evaluators detect AI work with 85.3% accuracy.
Shubham Vatsal, Harsh Dubey
A survey of 44 papers on 39 prompt engineering methods across 29 NLP tasks, showing how structured prompts improve LLM performance without retraining.
Yuqing Yang, Yan Ma, Pengfei Liu
Proposes a progressive weak-to-strong reasoning framework where a strong model refines its own training data without human or advanced model input, significantly improving reasoning on GSM8K and MATH.
Yu Wang, Shiwan Zhao, Zhihu Wang, et al.
SCoT improves LLM reasoning by first eliciting a problem-solving strategy before generating Chain-of-Thought steps, achieving significant gains on reasoning benchmarks.
Zhengren Wang, Jiayang Yu, Dongsheng Ma, et al.
RARE decouples knowledge storage from reasoning by externalizing domain knowledge to retrievable sources and internalizing reasoning patterns, enabling lightweight models to surpass GPT-4 and DeepSeek-R1 by ~20% accuracy.
Samar Khanna, Siddhant Kharbanda, Shufan Li, et al.
Mercury introduces diffusion-based LLMs for coding, achieving up to 10x throughput over speed-optimized models while maintaining comparable quality.
Keyon Vafa, Peter G. Chang, Ashesh Rambachan, et al.
Proposes an inductive bias probe to evaluate whether foundation models capture deeper domain structure, finding they often fail to generalize beyond training tasks.
Chengshuai Zhao, Zhen Tan, Pingchuan Ma, et al.
Proposes a data distribution lens to understand when and why Chain-of-Thought reasoning succeeds or fails, revealing it as a brittle mirage beyond training distributions.
E. Jahani, Benjamin S Manning, Joe Zhang, et al.
This paper shows that user prompt adaptation accounts for roughly half of performance gains from model upgrades in structured tasks but plays a limited role in open-ended creative tasks.