Transformer-based AI systems, like GPT-5.5 and AlphaFold 2, have achieved breakthroughs in scientific prediction and reasoning, with accuracy surpassing 90% in key benchmarks.

Petr O. Jedlicka

GD-RHCR framework, grounded in LI-MDP theory, guarantees near-optimality with significantly reduced computational cost for large-scale lifelong MAPF.

Alex DeWeese, Jiaoyang Li, Guannan Qu

This paper extends permanental process models by incorporating fixed effects via RKHS and the representer theorem, enabling interpretable parameter estimation.

Matthew LeDuc

This paper introduces ControlledShifts, a framework for standardized robustness evaluation in trajectory prediction under distribution shifts, combining a novel bias-controlled data splitting method with a unified performance score.

Ingrid navarro, Pablo Ortega-Kral, Yutong Duan et al.

Using geographically weighted random forest with TerraSAR-X, PlanetScope, and Sentinel-1 data, building height prediction RMSE is 5.34 meters in Porto Alegre.

Guilherme Iablonovski, Pierre-Louis Frison, Tatiana Silva da Silva

Optically writable atomic vapor RAM based on cesium vapor, enabling reservoir computing with 8 memory rails, 3.8 bits per rail, and a minimum BER of 0.02.

Elizabeth Robertson, Mingwei Yang, Lina Jaurigue et al.

Baobab compiles SROIQ ontologies into differentiable circuits, enabling robust neuro-symbolic learning with complex logic features.

Olga Mashkova, Asaad Mohammedsaleh, Fernando Zhapa-Camacho et al.

Proposes 'Entry Point Gates' to control cross-task usability; finds that binding location in understanding pathways enables concept transfer with minimal cost.

Zongyang Qiu, Yihan Wu, Kaixuan Fan et al.

Proposes a Bregman-distance-based regularization method in non-reflexive Banach spaces for statistical inverse problems, with theoretical guarantees and numerical validation.

Darrel K Joseph, M P Rajan

SRT, based on SuperMemo-2, dynamically schedules sample review, improving old knowledge retention by 5-37% while maintaining new learning.

Alankar Atreya, Devesh Batra, Yoages Kumar Mantri et al.

This study analyzes how LLM agents design AI methods, revealing heavy reliance on recombining human-designed algorithmic spaces, with limited innovation.

Yikang Yang, Zhengxin Yang, Luzhou Peng et al.

ASI-Bench evaluates AI's autonomous scientific exploration; scores drop from 50.91 to 26.62 as guidance decreases, showing reliance on human input.

Junwei Zhou, Zhen Sun, Binyu Li et al.

TSFT optimizes budget allocation via performance prediction and ILP, boosting task coverage by 2-3× in CRL under limited resources.

Jianan Zhou, Jung-Hoon Cho, Tianyue Zhou et al.

Proposes a Bethe free energy-based variational inference framework with an information constraint supporting message passing, enabling balanced exploration and exploitation.

Wouter M. Kouw

Proposes an efficient block encoding algorithm to tackle complexities in non-Abelian lattice gauge theory.

Patrick Draper

DiSCO reduces unsafe content in image generation via adversarial prompt optimization, achieving a 37.7% ASR reduction.

Tong Zhang, Motasem Alfarra, Carlos Hinojosa et al.

AutoSR employs Research-State Search with PW-MCTS to recover algebraically equivalent relations in nine benchmark problems, advancing symbolic regression towards automated scientific inquiry.

Kejia Zhang, Youran Sun, Xinyu Ren et al.

Introduced impression share prediction as an offline evaluation task using causal modeling, reducing prediction error by 49% on seen models and improving early-hour accuracy by 22%.

Mohsen Malmir, Houssam Nassif, Danish Nasir Shaikh et al.

Introduces Internal Compliance Score (ICS), a training-free activation readout that reveals rule blindness in compliance detectors, validated across multiple benchmarks and models.

Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu et al.

Proposes ESTI to detect state-semantic injection in LLM-driven embodied agents, evaluating downstream propagation of false environment states.

Jiawei Liu, Jiacheng Guo, Tian Zhang et al.