A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
K.A. Cobbina, Tianyi Zhou
First systematic study of how demo positions in prompts cause accuracy and prediction drift in LLMs, finding start-of-prompt placement yields +6 point gains.
S. Motwani, Alesia Ivanova, Ziyang Cai, et al.
Introduces a scalable method using curriculum RL on synthetically composed short-horizon data to boost long-horizon reasoning, achieving up to 2.06x accuracy gains on competition-level benchmarks.
Ahmed Heakl, Martin Gubri, Salman Khan, et al.
Dr. LLM retrofits frozen LLMs with lightweight routers trained via MCTS to skip, execute, or repeat layers, improving accuracy and efficiency without altering base weights.
Xiaoquan Chu, Tanlin Sun, Qian Li, et al.
PSPredictor uses machine learning on sequence features to predict liquid-liquid phase separating proteins, achieving 94.71% cross-validation accuracy.
Khalid M. Hosny, Akram M. Mortda, Nabil A. Lashin, et al.
A lightweight CNN with only four convolutional layers achieves high accuracy (99.1-100%) for detecting splicing image forgery across multiple datasets.
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.
Alexandria Leto, Cecilia Aguerrebere, I. Bhati, et al.
This paper investigates how retrieval accuracy affects RAG pipeline performance for QA tasks, finding that lowering search accuracy minimally impacts downstream quality while improving speed and memory.
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.
R. Doriguzzi-Corin, S. Millar, S. Scott-Hayward, et al.
Lucid is a lightweight CNN-based DDoS detection system that matches state-of-the-art accuracy with a 40x reduction in processing time, suitable for resource-constrained environments.
Joonho Lee, William J. Huggins, Martin Head‐Gordon, et al.
Introduces k-UpCCGSD, a sparse unitary coupled-cluster ansatz with O(kN) circuit depth for near-term quantum computers, achieving chemical accuracy at lower cost than UCCGSD and UCCSD.
Trevor E. Carlson, Wim Heirman, Stijn Eyerman, et al.
This paper evaluates high-level mechanistic core models, introducing the IW-centric model that balances simulation speed and accuracy for many-core processors.
Jessica Fridrich, Jan Kodovský
This paper introduces a novel strategy for building steganalysis detectors by assembling a rich model of noise residuals and using ensemble classifiers, achieving high detection accuracy against spatial-domain steganography.