PIDNet introduces a three-branch architecture inspired by PID control, achieving real-time semantic segmentation with superior speed and accuracy.

Jiacong Xu, Zixiang Xiong, Shankar P. Bhattacharyya

Introduces Capped Implicit Exploration (CIX) to balance bias-variance tradeoff in NeuRD, improving stability in non-stationary environments.

Dustin Morrill, Esra'a Saleh, Michael Bowling et al.

DPM-Solver uses analytical diffusion ODE solutions, enabling high-quality sampling in 10-20 steps, with 4-16× speedup over prior methods.

Cheng Lu, Yuhao Zhou, Fan Bao et al.

DepthShrinker merges linear layers by removing unimportant activation functions, boosting hardware utilization and achieving 3.06% accuracy gain and 1.53× throughput over SOTA pruning.

Yonggan Fu, Haichuan Yang, Jiayi Yuan et al.

Proposes proof production based on Farkas' lemma to enhance Simplex-based DNN verification, achieving 98% success with minimal overhead.

Omri Isac, Clark Barrett, Min Zhang et al.

Introduced a Generalized Delayed Feedback Model (GDFM) to enhance conversion rate prediction timeliness in recommender systems.

Jia-Qi Yang, De-Chuan Zhan

This paper introduces a modular framework for diffusion models, employing high-order Runge-Kutta sampling to reduce NFE to 35 while achieving SOTA FID of 1.79 on CIFAR-10.

Tero Karras, Miika Aittala, Timo Aila et al.

CoNSoLe uses double-convex deep Q-learning and Locally Convex Equation Learner for symbolic regression, improving accuracy.

Haoran Li, Yang Weng, Hanghang Tong

TransFuser employs multi-scale Transformer fusion of camera and LiDAR data, achieving 20% higher driving scores and 48% fewer collisions in dense traffic scenarios.

Kashyap Chitta, Aditya Prakash, Bernhard Jaeger et al.

SymFormer uses a Transformer-based architecture for symbolic regression, achieving fast and accurate inference.

Martin Vastl, Jonáš Kulhánek, Jiří Kubalík et al.

Post-hoc concept bottleneck models (PCBM) enable interpretable, high-performance neural networks without dense concept annotations, utilizing multimodal and residual techniques.

Mert Yuksekgonul, Maggie Wang, James Zou

Balanced EFCE-OMD makes Φ-Hedge polynomial-time in EFGs and achieves near-optimal \tilde{O}(√XAT) bandit trigger regret.

Yu Bai, Chi Jin, Song Mei et al.

Large-step GD can escape local minima and outperform small-step GD.

Amirkeivan Mohtashami, Martin Jaggi, Sebastian Stich

Proposes Hilbert Curve Projection (HCP) distance for efficient high-dimensional distribution comparison, with theoretical guarantees and superior empirical performance.

Tao Li, Cheng Meng, Hongteng Xu et al.

Proposes a continuous-time diffusion framework for discrete data using CTMCs, with Tau-leaping for efficient sampling, outperforming discrete methods.

Andrew Campbell, Joe Benton, Valentin De Bortoli et al.

Introduces leave-one-out spectral subspace perturbation bounds, improving clustering accuracy in mixture models with exponential error rates.

Anderson Y. Zhang, Harrison H. Zhou

Two-layer ReLU networks in teacher-student models outperform kernel methods, achieving near-global optimality at O(n^{-1}) rate.

Shunta Akiyama, Taiji Suzuki

EfficientViT achieves high-resolution dense prediction with multi-scale linear attention, reducing GPU latency by 13.9x.

Han Cai, Junyan Li, Muyan Hu et al.

GPT-3 model expresses uncertainty in natural language, tested with CalibratedMath suite.

Stephanie Lin, Jacob Hilton, Owain Evans

Diffusion-LM significantly enhances controllable text generation using continuous diffusion models, outperforming existing methods.

Xiang Lisa Li, John Thickstun, Ishaan Gulrajani et al.