MasRouter unifies collaboration mode, role allocation, and LLM routing, improving multi-agent system performance by 3.51% and reducing costs by over 52%.

Yanwei Yue, Guibin Zhang, Boyang Liu et al.

Using LLMs to generate interpretable mechanisms with constraint fixing, achieving competitive performance.

Jiayuan Liu, Mingyu Guo, Vincent Conitzer

SafeDialBench evaluates LLM safety across 22 scenarios and 7 attack strategies.

Hongye Cao, Sijia Jing, Yanming Wang et al.

Introduced Conv-LiGRU to reduce test-time overthinking, improving accuracy on CIFAR10-C.

Hieu Tran Bao, Nguyen Cong Dat, Nguyen Duc Anh et al.

CiteCheck introduces a large-scale Chinese citation faithfulness dataset using a two-stage manual annotation and LLM-based data augmentation, enabling efficient training of models with high robustness.

Ziyao Xu, Shaohang Wei, Zhuoheng Han et al.

NPSim transforms daytime images to nighttime using monocular inverse rendering and ray tracing, enhancing nighttime semantic segmentation.

Shutong Zhang

Weighted quantization using MMD via gradient flows shows significant MMD reduction in experiments.

Ayoub Belhadji, Daniel Sharp, Youssef Marzouk

This paper introduces frequency-guided noise scheduling in diffusion models, enhancing inductive biases and improving generation quality by manipulating spectral content.

Thomas Jiralerspong, Berton Earnshaw, Jason Hartford et al.

EMSYNC generates video soundtracks by aligning emotions and temporal boundaries, enhancing music-video synchronization.

Serkan Sulun, Paula Viana, Matthew E. P. Davies

LLM-powered agents enhance recommender systems through natural language interaction and explainability.

Qiyao Peng, Hongtao Liu, Hua Huang et al.

GNN+ framework enhances classic GNNs, outperforming SOTA Graph Transformers across 14 datasets with superior efficiency.

Yuankai Luo, Lei Shi, Xiao-Ming Wu

UniRoute uses feature vectors for dynamic routing, enabling efficient LLM inference across 30+ unseen models.

Wittawat Jitkrittum, Harikrishna Narasimhan, Ankit Singh Rawat et al.

TANTE employs neural Taylor expansion for time-adaptive operator learning, reducing error by 60-80% and speeding inference by 30-40%.

Zhikai Wu, Sifan Wang, Shiyang Zhang et al.

Introduces Drivership framework combining empirical, normative, and furtherance expectations to enhance AV driving behavior.

Laura Fraade-Blanar, Francesca Favarò, Johan Engstrom et al.

MAGELLAN uses metacognitive predictions to guide autotelic LLM agents in efficiently learning across large goal spaces.

Loris Gaven, Thomas Carta, Clément Romac et al.

Proposes CAM-UV-X, integrating residual and conditional independence tests, to identify causal directions amid hidden paths with theoretical guarantees.

Thong Pham, Takashi Nicholas Maeda, Shohei Shimizu

DMWM couples RSSM-S1 with LINN-S2 logic, improving long-horizon logical consistency by 14.3%.

Lingyi Wang, Rashed Shelim, Walid Saad et al.

VidCRAFT3 models interactions among geometry, motion, and lighting for precise image-to-video control.

Sixiao Zheng, Zimian Peng, Yanpeng Zhou et al.

Using computational intrinsic motivation, this study models the need for competence via reinforcement learning, revealing implicit assumptions in Self-Determination Theory.

Erik M. Lintunen, Nadia M. Ady, Sebastian Deterding et al.

CreAgent integrates game theory belief models and LLMs to simulate creator strategies, improving long-term recommender system evaluation.

Xiaopeng Ye, Chen Xu, Zhongxiang Sun et al.