Agile-WAM boosts robot control success by 29.4% with 11.9ms inference latency via multi-horizon multimodal prediction.

Hanchu Zhou, Brendan Lynch, Raman Goyal et al.

Introduces Prediction-Powered Smoothing (PP-S) and validation methods to enhance accuracy in disaggregated AI evaluation.

Sho Kawano, Zehang Richard Li, Paul A. Parker

OPTED fine-tunes end-to-end driving policies using a render-free teacher, improving driving scores by 1.6x and 9.5x.

Damiano Da Col, Maximilian Igl, Peter Karkus et al.

dQwen3.5 uses hybrid attention to achieve training loss in half the tokens compared to full-attention models.

Anton Xue, Litu Rout, Aditya Akella et al.

Instance-optimal adaptive location estimation via multiscale mid-summaries for all symmetric unimodal distributions.

Qiaosen Wang, Chao Gao

MILER achieves zero-shot sim-to-real transfer in unstructured environments using semantic mid-level representation.

Thomas Steinecker, Denis Trescher, Alexander Bienemann et al.

Introduces On-Demand Attention (ODA) method, significantly reducing global reads and enhancing long-context inference efficiency.

Haibo Feng, Ruiqi Liang, Hanyang Peng et al.

Proposed robust multi-task PCA method improves eigenspace estimation, reducing impact of outlier tasks.

Dali Liu, Haolei Weng

Proposes an underwater visual target tracking method combining target-specific depth estimation and adaptive model-fusion predictive control, outperforming existing frameworks.

Yuheng Zhou, Haiyang Cheng, Yanqi Feng et al.

ActObs method supervises observations to change exploration in RL, enhancing Qwen3 model performance on Terminal-Bench 2.0.

Juzheng Zhang, Disha Makhija, Manoj Ghuhan Arivazhagan et al.

MoWAM improves robot policy learning efficiency via explicit future motion prediction, showing strong performance on LIBERO dataset.

Jiayu Wang, Bin Zhu, Yue Yu et al.

Using prediction fragmentation to control test-time adaptation, significantly reducing harmful accepted area.

Lili Wang, Jing Li, Xiaowen Sun et al.

Improving marine perception with OceanSim's synthetic data generation pipeline.

Haoyu Ma, Onur Bagoren, Anja Sheppard et al.

Using the DAGMA algorithm, this paper identifies causal graphs and verifies edge direction identifiability in mixed datasets.

Sambit Mishra, Yingying Wang, Christine K. Johnson et al.

Study TAP approximation accuracy in spherical linear models, finding errors below fluctuation scale.

Jingbo Liu, Zhiyuan Yu

CoFree framework addresses reasoning collapse in LLM embedding learning, achieving a 2.8 nDCG@10 improvement.

Zihan Gong, Xiaohan Ye, Jiangchao Yao et al.

The study compares parallelism in three diffusion language models, finding Gaussian and uniform diffusion superior under certain conditions.

Sitan Chen, Liye Wang

Proves sharp spectral norm concentration for sparse random tensors, removing logarithmic factors.

Zhixin Zhou, Yizhe Zhu

Event log stochastic language analysis reveals concurrency indistinguishable; record activity times for clarity.

Antony R. Lee, Peter Tiňo, Iain B. Styles

OKSPCA combines random features and Adam update for supervised dimension reduction, showing pipeline-dependent performance across six benchmarks.

Zhenlin Yao, Wei Xiong