Proposes a heterogeneity-aware personalized federated learning model to enhance failure time prediction accuracy in industrial predictive analytics.

Yuhan Hu, Xiaolei Fang

FOCAL fuses coverage and anchoring attention to improve multi-label heterogeneous graph prediction, outperforming SOTA.

Chenghao Zhang, Qingqing Long, Ludi Wang et al.

S2MAM uses bilevel optimization for robust estimation and variable selection, validated on 16 datasets.

Xuelin Zhang, Hong Chen, Yingjie Wang et al.

Introduces Denoising Recursion Models (DRM), combining multi-step denoising with recursive inference, outperforming TRM on ARC-AGI with 8% accuracy gain.

Chris Cameron, Wangzheng Wang, Nikita Ivanov et al.

Sessa enhances long-range memory by embedding selective attention in feedback paths.

Liubomyr Horbatko

Introduced Bounded Ratio Reinforcement Learning (BRRL) framework, outperforming PPO in environments like MuJoCo.

Yunke Ao, Le Chen, Bruce D. Lee et al.

Apollo model integrates 28 medical modalities and 12 specialties to predict disease risk up to 5 years in advance.

Andrew Zhang, Tong Ding, Sophia J. Wagner et al.

Sonata is a 3.77M-parameter hybrid world model for six-axis IMU motion prediction, excelling in cross-cohort transfer under clinical data scarcity.

Blaise Delaney, Salil Patel, Yuji Xing et al.

ADAPT online reweighting dynamically adjusts sample importance via similarity signals, outperforming offline filtering, enhancing LLM generalization.

Wanru Zhao, Yihong Chen, Yuzhi Tang et al.

Analysis of generalization bounds in symbolic regression with genetic programming, revealing complexities in structure selection and constant fitting.

Masahiro Nomura, Ryoki Hamano, Isao Ono

Introducing SigGate-GT, a sigmoid gating mechanism that relaxes the softmax conservation constraint in graph transformers, improving stability and expressiveness.

Yang Liu, Dongxin Guo, Tom Zheng et al.

IDDM introduces controllable resampling via interpolation, improving discrete diffusion sample quality and flexibility.

Marcel Kollovieh, Sirine Ayadi, Stephan Günnemann

VS-WNO fails to translate spike sparsity into deployment cost advantage on Jetson Orin Nano.

Jason Yoo, Shailesh Garg, Souvik Chakraborty et al.

CaOPD framework decouples capability and calibration, reducing overconfidence by using empirical success rates, achieving better calibration without sacrificing accuracy.

Jiaxin Zhang, Xiangyu Peng, Qinglin Chen et al.

A smaller model post-trained with reinforcement learning excels in small-molecule drug design tasks, rivaling state-of-the-art frontier models.

Shriram Chennakesavalu, Kirill Shmilovich, Hayley Weir et al.

Task-reward optimization enhances Llama-3.2-3B-Instruct's performance on math datasets.

Sarthak Mittal, Leo Gagnon, Guillaume Lajoie

HILBERT framework achieves significant performance improvement in long-sequence audio-text representation learning through dual contrastive learning and information-balanced regularization.

Habibeh Naderi, Behrouz Haji Soleimani, Stan Matwin

Detect and suppress reward hacking using Gradient Fingerprints, achieving superior performance on math, code, and logical reasoning benchmarks.

Songtao Wang, Quang Hieu Pham, Fangcong Yin et al.

Proposes two uncoupled algorithms achieving last-iterate convergence at rate Ω(T^{-1/4}) in bandit feedback zero-sum games.

Côme Fiegel, Pierre Ménard, Tadashi Kozuno et al.

Prototype-Grounded Concept Models (PGCMs) verify concept alignment via visual prototypes, enhancing interpretability.

Stefano Colamonaco, David Debot, Pietro Barbiero et al.