Introducing LingT2I benchmark, analyzing cross-lingual performance gaps and cultural influences in multilingual T2I models.

Sicheng Zhang, Zhonghao Yan, Binzhu Xie et al.

Proposes EGVOR with evidence chain and hierarchical diagnosis, improving robustness by 15% in complex urban scenes.

Zhaoyang Wei, Bowen Jiang, Xumeng Han et al.

Combining Monte Carlo Dropout and input perturbations, the study assesses BERT variants' stability, finding RoBERTa most reliable with minimal output variance.

Pooja Yadav, Priyanka Harjule, Basant Agarwal et al.

MVTrack uses H.264 motion vectors for ultrafast, appearance-free moving object tracking; achieves high accuracy with minimal parameters and FLOPs.

Iñaki Erregue, Kamal Nasrollahi, Sergio Escalera

SkillLens uses Visual Skill Cards to improve GUI action prediction, boosting Step SR+11.6.

Zhou Liu, Ligang Huang, Zeli Su et al.

VGGD leverages pretrained geometric priors with dual-path architecture to enhance single-frame surround-view 3D reconstruction, achieving state-of-the-art results.

Junhong Lin, Jinlong Wang, Xianda Guo et al.

The study uses HHL and QSVT algorithms to solve Maxwell's equations, achieving state infidelities below 2·10^{-3} and success probabilities above 10^{-3}.

Francesco Turro, Marco Maronese, Daniele Dragoni

Simplax enhances discrete diffusion models by introducing simplex-valued variables, improving generative performance.

Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa et al.

Gaussian Sculpting employs end-to-end field optimization with bi-level training for high-quality surface reconstruction, achieving PSNR of 32.5dB on object scenes.

Ke Jiaxin, Juncheng Liu, Yi Wang et al.

AlignBlock module significantly enhances ViT data efficiency, boosting terminal scene mAP@50 to 0.973.

Haoran Sui, Yaoyuan Jia

This study demonstrates that iterative erasure count is not an affine-invariant concept dimension, highlighting the dependence on measurement procedures and geometric transformations.

Tingan Jin, Shuhang Dong, Haosong Li et al.

PCFlow achieves efficient image restoration through flow matching, significantly improving visual quality.

Sangwoo Jo, Donggeun Ko, Jayeon Kang et al.

EDPFRL-IM enhances personalized federated reinforcement learning through intrinsic motivation-driven exploration and privacy protection.

Md Rafid Islam, Rafsan Jany, Zahid Hasan et al.

Proposes a mixed-state quantum prototype framework for incremental learning, addressing capacity limits with minimal qubits and robust distance metrics.

Yu Wu, Qianli Zhou, Xinyang Deng et al.

Proposes EvoX Genesis, a persistent recursive world model enabling autonomous software evolution, successfully building a Rust C compiler and migrating MESA modules.

Beichen Huang, Zhenyu Liang, Bowen Zheng et al.

Introduces DSAgentBench, a benchmark for evaluating AI agents' ability to automate full data science workflows in real OS environments, achieving only 56.7% success.

Mizanur Rahman, Mohammed Saidul Islam, Ridwan Mahbub et al.

This study reveals that frozen brain MRI foundation models encode site information as a linearly decodable fingerprint, surpassing clinical variables, rooted in low-level image statistics.

Saman Rahbar

This paper introduces a GNN-guided genetic algorithm for supply chain optimization under cost uncertainty, significantly improving initial solution quality and robustness.

Faezeh Ardali, Gerald M. Knapp

Causal optimization framework using Transformer and Bayesian neural network improves recommendation incrementality by 7.20%.

Changshuai Wei, John Bencina, Phuc Nguyen et al.

MarkNull removes watermarks from AI-generated images via latent manipulation, reducing accuracy to 53.14% without visual degradation.

Jie Cao, Qi Li, Zelin Zhang et al.