Proposes Linear Optimal Transport (LOT) embedding for high-dimensional distribution classification, nearly matching Wasserstein-2 distances, especially effective under shift and scale perturbations.

Caroline Moosmüller, Alexander Cloninger

Proposed algorithm-independent lower bounds for Gaussian process bandit optimization, improving error probability dependence in standard and robust settings.

Xu Cai, Jonathan Scarlett

Using Fourier series analysis, this paper reveals how data encoding strategies influence the expressive power of variational quantum models, demonstrating universality with rich frequency spectra.

Maria Schuld, Ryan Sweke, Johannes Jakob Meyer

Compiling ONNX models using MLIR improves inference efficiency.

Tian Jin, Gheorghe-Teodor Bercea, Tung D. Le et al.

AB3DMOT employs 3D Kalman filtering and Hungarian matching, achieving 207.4 FPS with state-of-the-art accuracy on KITTI.

Xinshuo Weng, Jianren Wang, David Held et al.

Combines Lasso autoregression and DNNs, evaluating five markets over six years, with open-source tools for robust electricity price forecasting.

Jesus Lago, Grzegorz Marcjasz, Bart De Schutter et al.

S^3-Rec enhances sequential recommendation via mutual information maximization, addressing data sparsity.

Kun Zhou, Hui Wang, Wayne Xin Zhao et al.

HiPPO framework optimizes memory updates via polynomial projections, achieving 98.3% accuracy on permMNIST.

Albert Gu, Tri Dao, Stefano Ermon et al.

This survey reviews reinforcement learning (RL) methods for combinatorial optimization, focusing on TSP, from classical algorithms to deep RL with attention mechanisms, highlighting performance improvements.

Yunhao Yang, Andrew Whinston

Survey of active learning for text classification using DNNs, enhancing performance or reducing labeled data.

Christopher Schröder, Andreas Niekler

POP909 dataset offers 909 pop songs' piano arrangements, aiding music arrangement generation research.

Ziyu Wang, Ke Chen, Junyan Jiang et al.

Proposes a locally optimal design method using hybrid optimization to reduce network correlation impact on A/B test treatment effect estimation.

Qiong Zhang, Lulu Kang

Lift-Splat-Shoot framework enables end-to-end bird’s-eye-view encoding from multi-view images via implicit 3D unprojection, improving perception and motion planning.

Jonah Philion, Sanja Fidler

Proposes a scene-agnostic neural view synthesis method using SfM and MVS, outperforming state-of-the-art on Tanks and Temples with over 50% LPIPS reduction.

Gernot Riegler, Vladlen Koltun

Proposes a simple visual imitation interface using commercial reacher-grabber tools and SfM, achieving 87% success in pushing and 62% in stacking tasks.

Sarah Young, Dhiraj Gandhi, Shubham Tulsiani et al.

Proposes a precise bi-level optimization framework for adversarial injection attacks, significantly improving attack success and transferability, validated on real datasets.

Jiaxi Tang, Hongyi Wen, Ke Wang

TransNet V2 combines multi-scale 3D features and frame similarities, achieving F1 scores of 77.9%, 96.2%, and 93.9%.

Tomáš Souček, Jakub Lokoč

I2L-MeshNet predicts 1D lixel heatmaps and reaches 55.7 mm MPJPE on Human3.6M for monocular 3D mesh recovery.

Gyeongsik Moon, Kyoung Mu Lee

DIET-SNN optimizes membrane leak and threshold for low-latency, efficient deep SNNs, achieving 69% accuracy on ImageNet.

Nitin Rathi, Kaushik Roy

Proposes a nearly assumption-free causal inference method using high-order influence functions, validated in machine learning estimators.

Lin Liu, Rajarshi Mukherjee, James M. Robins