This survey reviews exploration techniques in deep reinforcement learning, including reward for novel states, diverse behaviors, goal-based, probabilistic, imitation, safe, and random methods.

Pawel Ladosz, Lilian Weng, Minwoo Kim et al.

DEIS employs exponential integrators for diffusion models, enabling high-fidelity sampling in as few as 10 steps, with FID 4.17 on CIFAR10 at 10 NFEs.

Qinsheng Zhang, Yongxin Chen

AGIC is an efficient approximate gradient inversion attack leveraging multi-epoch updates, achieving up to 50% PSNR improvement and 5x speed over SOTA.

Jin Xu, Chi Hong, Jiyue Huang et al.

Proposes Hypergraph Contrastive Collaborative Filtering (HCCF), integrating hypergraph structure learning and self-supervised contrast to improve recommendation robustness.

Lianghao Xia, Chao Huang, Yong Xu et al.

Bamboo enhances preemptible instance training resilience via neighbor node redundancy, boosting throughput 3.7× and cutting costs 2.4×.

John Thorpe, Pengzhan Zhao, Jonathan Eyolfson et al.

Presented Google Scanned Objects, a dataset of 1030 high-quality 3D scanned household items, enhancing robotic simulation and perception tasks.

Laura Downs, Anthony Francis, Nate Koenig et al.

Proposes an end-to-end Transformer for symbolic regression, directly predicting full expressions with constants, achieving near state-of-the-art accuracy with much faster inference.

Pierre-Alexandre Kamienny, Stéphane d'Ascoli, Guillaume Lample et al.

This study compares counterfactual and causal explanations in understanding categorical and continuous features, showing counterfactuals improve prediction accuracy and user preference.

Greta Warren, Mark T Keane, Ruth M J Byrne

Proposes Self-Calibrated Illumination (SCI) framework for fast, robust low-light image enhancement, outperforming SOTA with minimal parameters and high efficiency.

Long Ma, Tengyu Ma, Risheng Liu et al.

Transformer-based multi-label classification achieved F1 scores up to 0.9394 on COVID-19 literature topics.

Qingyu Chen, Alexis Allot, Robert Leaman et al.

Proposes sim-2-sim transfer with VLN BERT, boosting VLN-CE success rate by 12%.

Jacob Krantz, Stefan Lee

Proposes a trajectory-based online algorithm selection framework combining landscape and internal state features, with warm-starting, outperforming static strategies on BBOB and YABBOB datasets.

Ana Kostovska, Anja Jankovic, Diederick Vermetten et al.

MIRNet-v2 employs multi-scale residual blocks with attention mechanisms, achieving state-of-the-art results in image restoration tasks, reducing parameters by 81%.

Syed Waqas Zamir, Aditya Arora, Salman Khan et al.

Introduced IMCS-21 dataset to support five tasks in automatic medical consultation systems.

Wei Chen, Zhiwei Li, Hongyi Fang et al.

ELEVATER is the first benchmark and toolkit for evaluating language-augmented visual models across 55 datasets with diverse efficiency metrics.

Chunyuan Li, Haotian Liu, Liunian Harold Li et al.

IndicXNLI dataset created via high-quality machine translation, evaluating 11 Indian languages' cross-lingual inference with pretrained models.

Divyanshu Aggarwal, Vivek Gupta, Anoop Kunchukuttan

Proposed GNN-based RL approach significantly improves tensor network contraction paths, outperforming state-of-the-art methods.

Eli A. Meirom, Haggai Maron, Shie Mannor et al.

STONet leverages neural operators for spatio-temporal prediction, enhancing generalization to unseen spatial points.

Haitao Lin, Guojiang Zhao, Lirong Wu et al.

Self-Blended Images (SBI) enhances deepfake detection, achieving 99.64% AUC across datasets, improving cross-domain robustness.

Kaede Shiohara, Toshihiko Yamasaki

Proposed scenario-sampling framework significantly enhances efficiency in validating legged robot safety performance.

Bowen Weng, Guillermo A. Castillo, Wei Zhang et al.