This review summarizes large language models' applications, methodologies, and ethical challenges in finance, healthcare, and law.

Zhiyu Zoey Chen, Jing Ma, Xinlu Zhang et al.

Analyzes five major generative language models' biases in educational stories, identifying types of representational harms and their psychological impacts.

Faye-Marie Vassel, Evan Shieh, Cassidy R. Sugimoto et al.

Prometheus 2 merges models trained on direct assessment and pairwise ranking, achieving top correlation with human and GPT-4 judgments, across multiple benchmarks.

Seungone Kim, Juyoung Suk, Shayne Longpre et al.

MANTIS enhances multi-image vision language skills via instruction tuning, achieving 13-point improvement.

Dongfu Jiang, Xuan He, Huaye Zeng et al.

WildChat collected 1 million real user-chatbot interactions, revealing diverse use cases and toxicity issues, enabling model fine-tuning and safety analysis.

Wenting Zhao, Xiang Ren, Jack Hessel et al.

Proposes Large Tabular Model (LTM) as a foundational framework for structured data, emphasizing multi-task, cross-dataset, and generative capabilities.

Boris van Breugel, Mihaela van der Schaar

EchoScene employs a dual-branch diffusion model with information echo to generate 3D indoor scenes from scene graphs, enhancing controllability and global coherence.

Guangyao Zhai, Evin Pınar Örnek, Dave Zhenyu Chen et al.

Radar-based localization system for AGVs achieves accuracy comparable to lidar, with median errors of 0.013m/米 and 0.021°/米, suitable for low-power embedded hardware.

Andrew J. Kramer, Christoffer Heckman

Monte Carlo Tree Search and iterative preference learning enhance LLM reasoning, boosting accuracy to 81.8%.

Yuxi Xie, Anirudh Goyal, Wenyue Zheng et al.

Using Dreamer-v3 with tactile sensors enables autonomous robotic insertion, achieving up to 90% success in simulation and 75% in real-world tests.

Daniel Palenicek, Theo Gruner, Tim Schneider et al.

KAN, based on Kolmogorov-Arnold theorem, replaces fixed weights with learnable spline functions, outperforming MLP in accuracy and interpretability.

Ziming Liu, Yixuan Wang, Sachin Vaidya et al.

DOCCI dataset with 15k detailed image descriptions enhances fine-grained vision-language tasks.

Yasumasa Onoe, Sunayana Rane, Zachary Berger et al.

Proposes multi-token prediction to improve sample efficiency and inference speed; 13B model achieves 12% better problem-solving on code tasks.

Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière et al.

GS-LRM is a Transformer-based large-scale 3D reconstruction model that predicts high-quality scene primitives from 2-4 sparse views in 0.23 seconds.

Kai Zhang, Sai Bi, Hao Tan et al.

Proposed QGSO combines OptiFusion and EPJO for global automatic design of compound lenses, achieving 15% performance improvement.

Yao Gao, Qi Jiang, Shaohua Gao et al.

Proposed a multi-page Document VQA method using self-attention scoring, achieving state-of-the-art performance without OCR.

Lei Kang, Rubèn Tito, Ernest Valveny et al.

Proposes Scaffold-BPE, a dynamic token removal method that alleviates frequency imbalance, improving large language model training and performance.

Haoran Lian, Yizhe Xiong, Jianwei Niu et al.

Deep learning models (e.g., LSTM, CNN) decoded EEG signals achieving 85% character accuracy.

Saydul Akbar Murad, Nick Rahimi

Unified data-dependent generalization bounds via PAC-Bayesian on random sets, applied to fractal dimension and Langevin dynamics.

Benjamin Dupuis, Paul Viallard, George Deligiannidis et al.

LM-IGTD transforms low-dimensional and mixed-type tabular data into images using noise augmentation and improved IGTD, boosting CNN classification performance.

Vanesa Gómez-Martínez, Francisco J. Lara-Abelenda, Pablo Peiro-Corbacho et al.