Self-Policy Distillation (SPD) extracts low-rank capability subspaces via gradients, guiding self-generation without external signals, improving performance by 13%.

Guangya Hao, Yitong Shang, Yunbo Long et al.

Proposes EMO-STA, a multi-task evolutionary framework leveraging shared program archives, improving efficiency and generalization in LLM-guided program discovery.

Halil Alperen Gozeten, Xuechen Zhang, Emrullah Ildiz et al.

Proposed Branch-Stochastic MPC with scenario clustering improves safety and real-time performance in multi-modal uncertainty motion planning.

Zekun Xing, Ramkrishna Chaudhari, Marion Leibold et al.

SynAE employs multi-metric evaluation to assess synthetic data quality for tool-calling agents, focusing on validity, fidelity, and diversity, enabling robust benchmarking.

Shuaiqi Wang, Aadyaa Maddi, Zinan Lin et al.

Proposed Quantum Genetic Negative Selection Algorithm (QGNSA) achieves superior anomaly detection accuracy on Metaverse Financial Transactions Dataset.

Giancarlo P. Gamberi, Calebe P. Bianchini

Directly evaluate harness optimizers via priority ranking; correlation ρ=0.602.

Kai Tzu-iunn Ong, Minseok Kang, Dongwook Choi et al.

Neural compiler converts symbolic physics programs into exact, differentiable PyTorch modules, enabling precise, composable hybrid models with minimal parameters.

Lucas Sheneman

Proposes a three-step evaluation protocol addressing biases of pointwise metrics in multimodal inverse problems, emphasizing distribution fidelity and calibration.

Mads H. Baattrup, Jörn Bach, Laurids Jeppe et al.

Steins;Gate Drive employs structured future forecasting with latency decoupling, significantly improving autonomous driving safety and responsiveness.

Anjie Qiu, Hans D. Schotten

QuantSR+ introduces RBD, QSA, and SFD techniques to achieve ultra-low-bit image super-resolution, outperforming existing methods in accuracy and efficiency.

Haotong Qin, Xudong Ma, Xianglong Liu et al.

PIU uses proximity-guided replacement in Arc2Face to effectively erase target identities, improving privacy protection with minimal impact.

Jose Edgar Hernandez Cancino Estrada, Mauro Díaz Lupone, Žiga Emeršič et al.

SOMA employs multi-view spatial memory to enable out-of-vision manipulation, boosting success rates by 10% in real-world tasks.

Pengteng Li, Weiyu Guo, He Zhang et al.

Proposed Bayesian object classification via OSINT-aided heterogeneous sensor fusion, achieving 95% accuracy.

Jan Nausner, Michael Hubner

Data gating is critical for self-play RL stability; reward signals alone cannot prevent collapse.

Sophia Xiao Pu, Zhaotian Weng, Chengzhi Liu et al.

NoPo4D employs velocity decomposition within a 4D Gaussian framework for real-time, pose-free multi-view dynamic scene reconstruction, outperforming prior methods.

Matteo Balice, Yanik Kunzi, Chenyangguang Zhang et al.

AVP model enhances robotic task success rate by 37.04% using visual primitives.

Weilong Guo, Yuchen Wang, Renping Zhou et al.

Proposes three LLM-based planner generation methods—search code, PDDL models, and policies—focused on reliable, resource-efficient construction.

Michael Katz, Harsha Kokel, Kavitha Srinivas et al.

EvoScene-VLA updates scene states via actions, boosting RoboTwin task success to 88.8%.

Chushan Zhang, Ruihan Lu, Jinguang Tong et al.

Introduces stable-worldmodel (swm), a unified platform supporting reproducible research with high-performance data loading, multiple world model baselines, and diverse environment benchmarks.

Lucas Maes, Quentin Le Lidec, Luiz Facury et al.

RankJudge generates multi-turn dialogue benchmarks, using the Bradley-Terry model to evaluate 21 LLM judges.

Zhenwei Tang, Zhaoyan Liu, Rasa Hosseinzadeh et al.