CorporateBench is a large-scale, temporally evolving knowledge base benchmark for multi-task enterprise QA, with over 230,000 documents.

Sil Hamilton, Albert Yu Sun, Oscar J. Romero et al.

Establishes a sharp phase transition threshold for ellipsoid fitting in high dimensions, depending solely on the fourth moment of the data distribution, using random matrix and convex optimization techniques.

Frederic Koehler, Youngtak Sohn

Proposes ESRP task with egocentric observations and top-down layouts; introduces ESRP-Bench with 5400+ scene pairs; baseline success only 30.2%.

Canzhi Chen, Zan Wang, Siqi Zhu et al.

Introduces the concepts of information floors and model gaps, quantifying the limits of parallel draft acceptance; results show models are far above their theoretical bounds.

Xinwei Qiang, Xiang Fang, Chang Chen et al.

Using critic-sourced artist relations and 80 acoustic features with Wasserstein distance, the study validates their musical similarity (AUC 0.767)

Elena Badillo-Goicoechea, Fengfeng He

Proposed TADP: task-aware deformable prediction for single-stage 3D detection, achieving 80.91% mAP on KITTI.

Su Wang, Yaochen Li, Min Yang et al.

MILP-based optimization framework for large-scale MAV fleet scheduling, maximizing data collection with energy and time constraints.

Mehdi El Krari, Jonathan Smith, Maria Fox

DINOcular integrates depth priors with self-supervised vision transformers, boosting 3D spatial understanding by 15% on Probe3D benchmarks.

Farkhat Almukhamedov, Sami Azirar, Hermann Blum

PACE achieves 93.8% performance retention while reducing visual tokens by 90%, enabling a 3.1x speedup via pixel compression and dual-attention extraction.

Junjie Liu, Shengyuan Ye, Xu Chen

Using ANTShapes simulated datasets, combined with convolutional SNNs, for event-based object classification, validating data quality and robustness.

M. Middleton, H. Kayan, B. Sen Bhattacharya et al.

TRACE-CRC employs trajectory-adaptive conformal risk control for multi-step CSI prediction, achieving 0.933 coverage with smaller uncertainty balls.

Kiarash Rezaei, Mehdi Sattari, Javad Aliakbari et al.

Introduced DocTalkBN, a large-scale multimodal Bengali medical dialogue dataset with 557.63 hours, supporting triage, safety, and NER tasks.

Anik Saha, Fahmida Sultana Naznin, Sadatul Islam Sadi et al.

SPEA-2-based multi-objective algorithm improves bug localization accuracy to 88.5%.

Waleed Ahmad, Mehtab Kiran Suddle, Maryam Bashir

Introduces a third-order Taylor expansion-based single communication federated inference, improving accuracy in small, skewed datasets.

Laura Montagnani, Anthony CC Coolen, Marianne A Jonker

Cascaded Batch Prompting improves performance by disentangling complex reasoning from symbol grounding.

Sho Hoshino, Peinan Zhang

KinyaEmbed improves Kinyarwanda sentence embeddings via a four-stage curriculum, achieving Spearman ρ=0.7298.

Ireddi Rakshitha, Devavarapu Yashwanth, Ntakirutimana Pierre

Introduces feature geometry-based covariance envelope bounds under volume sampling, with a sharp phase boundary defined by feature margin ν_A.

Kihun Rhee

Nested-EAGLE model integrates short- and medium-range forecasts, significantly reducing MSE over CONUS.

Timothy A. Smith, Mariah Pope, Sergey Frolov et al.

HOLMES achieves 5.9% error in high-dimensional settings with a 58.8x speedup.

Wei W. Xing, Xixi Zhou, Kaiqi Huang et al.

WM-R1 replaces real environments with world models, significantly enhancing GUI agents' reasoning capabilities.

Yu Han, Tianwen Qian