GUI-CIDER enhances GUI agent training via causal internalization and density-aware exemplar reselection, boosting task success by 9.70%.

Zheng Wu, Chengcheng Han, Zhengxi Lu et al.

This study analyzes how sample difficulty influences RLVR, revealing medium difficulty samples yield the strongest and most stable reasoning improvements.

Yue Cheng, Jiajun Zhang, Xiaohui Gao et al.

Hybrid neural world models with multi-horizon prediction and error maps enable fast, reliable physical simulations, especially at shocks and contacts.

Pranav Lakshmanan, Paras Chopra

Proposed a provably guaranteed polytopic uncertainty quantification framework for 3D SLAM, ensuring true poses are within certified sets with high probability.

Guangyang Zeng, Yulong Gao, Yuan Shen et al.

FT-Pilot uses GNN for vulnerability prediction and LLM for RTL rewriting, reducing soft-error error rates by over 85% in automated reliability optimization.

Weixing Liu, Zizhen Liu, Jing Ye et al.

StayFair ensures group fairness in diffusion models across guidance scales, improving fairness by 8.6%.

Myeongsoo Kim, Eunji Kim, Minwoo Chae et al.

MemGuard uses a type-aware framework to reduce memory contamination, improving memory reliability by 28.27%.

Hyeonjeong Ha, Jeonghwan Kim, Cheng Qian et al.

ROVER enhances multi-image reasoning accuracy via object-centric visual evidence routing.

Guannan Lv, Ren Nie, Hongjian Dou et al.

Introduces a measurement-based soft PCA using Fermi-Dirac filtering, avoiding eigenvector recovery, suitable for quantum data with dimension-independent sample complexity.

Yewei Yuan, Michele Minervini, Mark M. Wilde et al.

AI research agents generate more concentrated scientific ideas, failing to significantly broaden scientific exploration.

Yixuan Tang, Yi Yang

AIBuildAI-2 uses hierarchical knowledge system to automate AI model building, achieving 70.7% medal rate.

Ruiyi Zhang, Peijia Qin, Qi Cao et al.

Introduces AndroidDaily benchmark and GRADE evaluator, enabling automatic verification of GUI agents in real-world closed-source apps.

Yifan Sui, Xin Huang, Hongbing Li et al.

STROP improves structural scene representation by learning variable-length visual programs.

Piotr Wyrwiński, Kacper Dobek, Krzysztof Krawiec

Proposes AW–NBE combining neural Bayes and Sinkhorn divergence for likelihood-free inference in multivariate generalized Pareto models.

Samira Aka, Marie Kratz, Philippe Naveau

Proposes removal-based attribution framework for multi-agent LLMs; LOO achieves 7.5× efficiency, boosting task performance by 17%.

Mingyu Lu, Yushan Huang, Chris Lin et al.

Using pymetrics data, reveals algorithmic monoculture causes racial disparities and systemic rejection in hiring.

Rishi Bommasani, Sarah H. Bana, Kathleen A. Creel et al.

MUSE-Autoskill improves task success to 68.4% via unified skill lifecycle management and cross-agent skill transfer.

Huawei Lin, Peng Li, Jie Song et al.

LocateAnything uses Parallel Box Decoding and 138M samples to significantly boost visual grounding speed and accuracy.

Shihao Wang, Shilong Liu, Yuanguo Kuang et al.

BRANE uses LLM-extracted query features to dynamically optimize retrieval configurations, achieving up to 89% cost savings on MuSiQue and others.

Melissa Z. Pan, Negar Arabzadeh, Mathew Jacob et al.

SAERL leverages Sparse Autoencoder activations to model diversity, difficulty, and quality for LLM post-training data engineering, boosting Qwen2.5-Math-1.5B accuracy by 3%.

Yi Jing, Zao Dai, Jinwu Hu et al.