UniMPA addresses transition realizability in VLA models via action-grounded transition modeling.

Wei Li, Rui Shao, Jie He et al.

FARM reads frozen VLA-JEPA states with 33,985 parameters, reaching 85.68% AUROC and 88.59% AUPRC.

Haoran Pei, Mingrui Luo, Senbao Wang et al.

ReconPlusGen injects reconstruction priors into multi-view 3D generation via noise inversion, significantly enhancing reconstruction accuracy.

Jiarui Liu, Heng Li, Weiyu Li et al.

Using bound propagation to verify steering in unseen conditions for autonomous vehicles.

Menuka Ghalan, Charles Rodgers, Zachary D. Asher

CamPilot uses a multi-agent framework to enhance cinematographic control and quality in movie generation.

Yang Wu, Stefano Petrangeli, Ishita Dasgupta et al.

Using semantic uncertainty to predict transition relevance places (TRPs) significantly outperforms baseline methods.

Muhammad Umair, Jan P. de Ruiter

scDEFT predicts drug effects using deep learning, achieving AUROC of 0.70.

Murthy Devarakonda

The study introduces META-AGENT for task-agnostic preprocessing in unknown environments, achieving highest Avg@3 reward on five benchmarks.

Vinay Samuel, Varun Ursekar, Vijay S. Kalmath et al.

Introduced Programmable World Model, achieving 94% Count Accuracy and 98% State Accuracy by decoupling state evolution from visual generation.

Zheng-Hui Huang, Guixu Lin, Jiacheng Lin et al.

Proposes finite witness assignments and a separation-width hierarchy to characterize language generation in the limit, verified in Lean.

Xiaoyu Li, Andi Han, Jiaojiao Jiang et al.

Proposes a Gaussian joint measurement-based protocol for low-rank quantum state tomography, optimizing sample complexity to Θ(dr/ε²).

Ashwin Nayak, Xingyu Zhou

DUET-DINO enables 7-DoF robot planning via cross-view latent world modeling, achieving 92%-60% task success rates.

Nisarga Nilavadi, Ralf Römer, Moritz Reuss et al.

Using IQP circuits, Logistic Regression's F1 improves from 0.462 to 0.517, outperforming Kernel PCA.

Menachem Finkelstein, Diana Legziel Levy, Zohar Yakhini et al.

Field Converter reduces player pose estimation error in soccer broadcasts from 49cm to 10cm using geometry initialization and temporal residual refinement.

Simon Khan, Laurent Gajny, Jennyfer Lecompte et al.

Proposed RBQE framework uses cross-model agreement to estimate polyp segmentation reliability, achieving ROC-AUC of 0.960.

Siddharth Gupta, Jitin Singla

IBIB protocol evaluates enterprise AI systems via serving routes, not model identifiers, improving reliability measurement.

Blake Stenstrom, Charangan Vasantharajan, Brian Sathianathan

Introduces covariance neural networks (VNNs), combining PCA and graph learning to improve stability and transferability on multiscale datasets.

Saurabh Sihag, Andrea Cavallo, Elvin Isufi et al.

Introduced Semigroup-JEPA for zero-shot physics generalization, achieving 34% error reduction and 23.3% control success improvement.

Andy Zeyi Liu, Haoran Sun, Lucas Baker et al.

JarvisGUI evaluates cross-device GUI agents with dynamic task composition, revealing capability gaps in real-world workflows.

Zixiang Chen, Yuheng Lu, Zihao Cheng et al.

ConvMem reformulates long-context reasoning as hierarchical convolution, outperforming training-free baselines on RULER-HotpotQA.

Hongming Zhang, Zhaozhen Gu, Fengshuo Bai et al.