Unified ABM framework models opinion change via attitude update, choice, and message functions, incorporating four key influence mechanisms.

Yun-Shiuan Chuang, Timothy T. Rogers

Inference-time intervention (ITI) shifts activations in select attention heads to improve LLaMA's truthfulness from 32.5% to 65.1%, using minimal data and computational cost.

Kenneth Li, Oam Patel, Fernanda Viégas et al.

Combining GPT-3.5-turbo and BLIP-2, the method improves OSM road tagging accuracy by up to 29%.

Levente Juhász, Peter Mooney, Hartwig H. Hochmair et al.

CMExam is the first Chinese medical exam dataset with comprehensive annotations; GPT-4 achieved 61.6% accuracy on it.

Junling Liu, Peilin Zhou, Yining Hua et al.

Proposes nonparametric iterative machine teaching (NIMT) via functional optimization; introduces random and greedy algorithms with theoretical ITD bounds.

Chen Zhang, Xiaofeng Cao, Weiyang Liu et al.

Whisper outperforms XLS-R in diverse Arabic conditions but struggles with unseen dialects.

Bashar Talafha, Abdul Waheed, Muhammad Abdul-Mageed

Video-LLaMA integrates Video Q-former and Audio Q-former for audio-visual understanding.

Hang Zhang, Xin Li, Lidong Bing

VideoComposer employs motion vectors and spatio-temporal encoding to enable multi-modal controllable video synthesis with high temporal consistency.

Xiang Wang, Hangjie Yuan, Shiwei Zhang et al.

A layered risk assessment and dynamic safety lifecycle framework constructs a credible autonomous driving safety case.

Francesca Favaro, Laura Fraade-Blanar, Scott Schnelle et al.

Proposes Fine-Grained RLHF, using dense, multi-category rewards to improve language model training, reducing toxicity and factual errors.

Zeqiu Wu, Yushi Hu, Weijia Shi et al.

Proposed GODE framework employs bi-level contrastive learning to fuse molecular graphs with knowledge graph substructures, boosting molecular property prediction by 12.7% ROC-AUC and 34.4% RMSE/MAE.

Pengcheng Jiang, Cao Xiao, Tianfan Fu et al.

Proposes Attentive Kernel (AK), a non-stationary GP kernel, improving environmental modeling and active sampling in robotics.

Weizhe Chen, Roni Khardon, Lantao Liu

RefinedWeb dataset uses rigorous filtering and deduplication on web data alone, training models that outperform The Pile with 5 trillion tokens, matching GPT-3 performance.

Guilherme Penedo, Quentin Malartic, Daniel Hesslow et al.

Proposed new non-commutative matrix multiplication algorithms reducing multiplication count for certain formats.

Manuel Kauers, Jakob Moosbauer

This paper introduces the Galerkin method for spectral algorithms, outperforming graph Laplacian approaches, especially in high-dimensional and large-scale settings, with efficient structured kernel implementation.

Vivien Cabannes, Francis Bach

DiffLL enhances low-light images using Wavelet-based Conditional Diffusion Model, improving efficiency by 70x.

Hai Jiang, Ao Luo, Songchen Han et al.

FlowCam trains generalizable 3D radiance fields without camera poses using pixel-aligned scene flow, enhancing 3D reconstruction from video data.

Cameron Smith, Yilun Du, Ayush Tewari et al.

This survey categorizes LLM-based recommendation into discriminative (e.g., BERT) and generative (e.g., GPT) paradigms, analyzing their techniques and performance.

Likang Wu, Zhi Zheng, Zhaopeng Qiu et al.

A geometric regularization approach to handle noise in deep constrained clustering, significantly improving accuracy.

Tri Nguyen, Shahana Ibrahim, Xiao Fu

This study evaluates GPT-4's geographic knowledge across tasks like location, distance, and topography, highlighting strengths and limitations.

Jonathan Roberts, Timo Lüddecke, Sowmen Das et al.