Using ordinal pattern analysis and information-theoretic measures, the study achieves 99% accuracy in classifying 14 Peruvian news sources based on structural features.

Cynthia Z. Zhou-Lin, José L. Herrera-Diestra, Luciano Stucchi

PerceptionBench evaluates atomic visual perception in MLLMs; highest accuracy among 16 models is only 59.7%.

Zichao Lin, Yifeng Xie, Bowen Qu et al.

Mage-VL employs Codec-native sparse token encoding, reducing 75% tokens and achieving 3.5× inference speedup for real-time multimodal streaming.

Senqiao Yang, Kaichen Zhang, Zhaoyang Jia et al.

Proposes AUC of Pareto frontier for efficiency evaluation; introduces fluid search, outperforming fixed strategies in 12 tasks.

Haiqian Yang, Yuan Cao

PARED employs inverse RL in feature space to extract implicit rewards from demonstrations, improving language model alignment without task-specific annotations.

Michał Wiliński, Liu Leqi, Chirag Nagpal

CameraAnything integrates pixel-level Plücker rays and resolution-aware 3D RoPE in a diffusion framework for joint camera parameter control, supporting viewpoint, focal length, and resolution adjustments.

Yixuan Li, Yanhong Zeng, Ka Leong Cheng et al.

Selective tuning of the last three ViT layers with HYBRID16 gives a 2B model 68.8% temporal mIoU from 16 frames.

Jiameng Zhang, Srikanth Madikeri

HG-CRC controls hierarchical group risk; on ARC Challenge it achieved 0% empirical violations and WGER=0.

Murilo Salem, Luísa Böhm, Daniel Pontes et al.

FlowCTS replaces KL-OPD with trajectory supervision, raising GenEval to 0.93, OCR to 0.92, and PickScore to 23.06.

Kaiyang Ye, Yuan Ge, Junxiang Zhang et al.

SciConsolidate synthesizes procedural knowledge to enhance scientific computing, improving Qwen3.6-27B by 6.26 points.

Liwei Dong, Jiahao Zhao, Nan Xu

MSVS-VAE employs hierarchical point-shuffle upsampling and local AVS-Conv to achieve high-fidelity 3D reconstruction, 10× faster decoding, and 10× more compactness.

Dehao Hao, Kaiyi Zhang, Tanghui Jia et al.

RecursiveECG uses evidence-based recursive refinement, transforming expert ECG criteria into validated measurements to improve classifier performance by 10% on benchmark datasets.

Jinliang Deng, Yiming Niu, Yibo Pan et al.

TaoMate employs anchor-guided persistent memory, enabling stable real-time long-form audio-video generation with 97.55% appearance consistency and 16.32FPS speed.

Qijun Gan, Chenwei Zhang, Meiguang Jin et al.

Proposes TSDF-confidence-based quality-adaptive multi-UAV exploration, improving path efficiency and reconstruction fidelity.

Benjamin Sportich, Kenza Boubakri, Olivier Simonin et al.

Model-Driven Engineering (MDE) enables scalable SSH workflows, reducing GPU hours from 9000 to 92 for classifying 220 million records.

Joan Giner-Miguelez, Alexandra Málaga, Felipe Gómez-Cortés et al.

Proposes State Transition Pretraining (STP) using joint inverse and forward dynamics to enhance GUI agents, improving success rates by up to 6.2%.

Xiangyan Liu, Kaixin Li, Haonan Wang et al.

SpecFormer introduces spectral softening and spectral-aware attention to mitigate embedding and attention collapse in recommendation Transformers.

Yu Cui, Yi Xu, Jiahao Wang et al.

Mechanism mapping reveals evolutionary paths from cognitive architectures to language agents, identifying five residual bundles for future integration.

Haodi Fan, Zucong Lan

Proposes BC-NMPC integrating battery and propulsion models for real-time thrust prediction and trajectory replanning in high-speed UAV flight.

Parakh M. Gupta, Matej Mihulka, Matej Novosad et al.

CALM trains language models via multi-task RL over structured controllers, enhancing generalization across diverse inference workflows.

Moumita Choudhury, Vanshaj Khattar, Jing Liu et al.