On Navier-Stokes benchmark, ConvAE-Relay achieves 38.34% error under 10x Reynolds shift, outperforming FNO's 46.68%.

Jianing Shi

Multi-horizon horizon-aware GCN emulator improves long-term ice sheet forecasts, reducing RMSE by 25% over 20-year simulations.

Zesheng Liu, Maryam Rahnemoonfar

Proposes Cayley-Table Completion with tensor factorization and flatness prior to recover discrete algebraic structures via continuous optimization.

Dongsung Huh

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.

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

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

LearnWeak framework uses a stronger reference agent to identify model weaknesses, synthesizes targeted tasks, and improves small CUAs by 11.6% on average across 8 domains.

Suji Kim, Kangsan Kim, Sung Ju Hwang

H-consistency framework for multi-label metric optimization; introduces O(l) surrogate loss with exact decomposition.

Mehryar Mohri, Yutao Zhong

BIRDNet encodes mined Boolean implication graphs into sparse, interpretable deep neural networks, achieving near state-of-the-art AUROC with 96x fewer active parameters on six biomedical datasets.

Tirtharaj Dash

SHIFT method selects data using inference-time hidden-state dynamics, enhancing RLVR performance.

Jianghao Wu, Jianfei Cai, Weiqiang Wang 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

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.

Proposed GADD algorithm achieves O(polylog(ε⁻¹)) sampling complexity for uniform-rate discrete diffusion models, significantly accelerating sampling.

Yuchen Liang, Ness Shroff, Yingbin Liang

Proposed Normal Guidance regularization improves attention-based MIL slice-level localization on 4M+ CT slices, outperforming baselines.

Ethan Harvey, Dennis Johan Loevlie, Michael C. Hughes

ReMoE boosts expert reuse by 26% through router fine-tuning in memory-constrained MoE inference.

Xiongwei Zhu, Xiaojian Liao, Tianyang Jiang et al.

Symmetric Attention Decomposition uses Hopfield stability and skew circulation to control SDXL’s fidelity–diversity trade-off.

Hyunmin Cho, Woo Kyoung Han, Kyong Hwan Jin

Introduces teachability metric for token selection in on-policy distillation, improving performance with only 5% tokens.

Yuanyi Wang, Su Lu, Yanggan Gu et al.

Unified Neural Scaling Law (UNSL) models multi-dimensional scaling of deep networks, improving performance extrapolation accuracy by over 10%.

Ethan Caballero, Priyank Jaini, David Krueger et al.

LoopMDM employs selective layer looping, reducing training FLOPs by 3.3× while matching or surpassing baseline performance, with flexible inference scaling.

Sanghyun Lee, Chunsan Hong, Seungryong Kim et al.

Proposed CoAD fuses classification and reconstruction with probabilistic soft masking, boosting time series anomaly detection accuracy.

Qideng Tang, Dai Chaofan, Wubin Ma et al.

ReWA combines reparameterization, weight decay, and adaptive learning rate to enhance sparse optimization, addressing instability and improving pruning in deep models.

Huangyu Xu, Jingqin Yang, Qianqian Xu et al.