Rec-Distill employs decoupled training to distill 24B-parameter teacher models, achieving over 60% transferability in industrial recommendation tasks.

Haoran Ding, Wenlin Zhao, Yuchen Jiang et al.

UKA introduces user-aware active knowledge acquisition using ToM uncertainty, boosting emotional support dialogue quality.

Mufan Xu, Kehai Chen, Jiahao Hu et al.

GODeform framework leverages geometry-guided feature modeling to achieve significant improvements in monocular 3D shape recovery.

Yiyao Ma, Kai Chen, Zhongxiang Zhou et al.

SCOPE integrates a frozen LLM with an open-set plugin classifier, achieving 91.05% open-set detection accuracy and 96.63% anomaly correction in ATC readback monitoring.

Qihan Deng, Minghua Zhang, Yang Yang et al.

UI-KOBE enhances lightweight GUI agents with app-specific graph knowledge, boosting task success rate to 77.6%.

Yuxiang Chai, Han Xiao, Xinyu Fu et al.

DistractionIF reveals inverse scaling in large models under distractor instructions; GRPO improves robustness by 15.5%.

Zeli Su, Zhankai Xu, Tianlei Chen et al.

PhoneWorld converts real GUI trajectories into scalable phone-use environments, boosting evaluation benchmarks by 52.5 points.

Yuxuan Liu, Xin Lai, Junyi Li et al.

Proposes a Schrödingerization-based quantum IMEX scheme with parameter-independent complexity for multiscale PDEs.

Qitong Hu, Xiaoyang He, Shi Jin et al.

Proposes Draft-OPD, combining target supervision and error replay, achieving 5× speedup in large language model inference.

Haodi Lei, Yafu Li, Haoran Zhang et al.

WorldMemArena evaluates multimodal agent memory, revealing flexible yet unreliable memory management.

Chengzhi Liu, Yuzhe Yang, Sophia Xiao Pu et al.

This paper reexamines FID, revealing its dependence on reference dataset geometry, emphasizing the importance of integrating geometric features for reliable evaluation.

Yunghee Lee, Byeonghyun Pak

STAMP framework trains explicit memory for mobile GUI agents using controllable virtual environments, enhancing Memory-World benchmark performance.

Junyang Wang, Haiyang Xu, Xi Zhang et al.

Introduces subspace-constrained preconditioning via QR-like factorization, enhancing randomized iterative methods' convergence.

Yonghan Sun, Hou-Duo Qi, Deren Han et al.

Improved search conversion rate prediction by scaling model backbone, embedding parameters, and training data, achieving a +2.6% increase.

James Pak, Jyun-Yu Jiang, Fan Zhang et al.

BenchTrace evaluates LLM reflection and controlled evolution using 1821 annotated failure episodes, introducing FAR as a key metric.

Jiahao Huang, Fei Cheng, Junfeng Jiang et al.

ReasonOps identifies seven operators in LLM reasoning traces using unsupervised methods, achieving 76% accuracy.

Daniel Lee, Owen Queen, James Zou

Proposed Influence-Guided Symbolic Regression (IGSR), combining LLM generation and influence scores for scientific discovery.

Evgeny S. Saveliev, Samuel Holt, Nabeel Seedat et al.

Proposes a variational quantum algorithm for nonlinear finite element analysis of hyperelastic materials, using polynomial approximation within a hybrid quantum-classical framework.

Uditnarayan Kouskiya, Caglar Oskay

Introduces Diffused Geodesic Moments (DGM), excelling on FAUST-Reg and TOSCA datasets.

Zhicheng Du, Changyue Liu, Wenji Xi et al.

Proposed hardware-tailored resource estimation for magic-state distillation on silicon spin qubits, analyzing overheads with realistic noise models.

Songqinghao Yang, Christopher K. Long, Rubén M. Otxoa et al.