Proposed HUMANISE dataset and scene-language conditioned generative model achieve diverse, semantically consistent 3D human motions, with key metrics showing 15% improvement over baselines.

Zan Wang, Yixin Chen, Tengyu Liu et al.

Imagic uses diffusion models for complex text-guided edits on a single real image.

Bahjat Kawar, Shiran Zada, Oran Lang et al.

Simple prompts enhance GPT-3's reliability in generalizability, social bias, calibration, and factuality.

Chenglei Si, Zhe Gan, Zhengyuan Yang et al.

Proposes a human-centered AI robustness framework, integrating method taxonomy and evaluation metrics, emphasizing human expertise in robustness enhancement.

Andrea Tocchetti, Lorenzo Corti, Agathe Balayn et al.

Proposes design-based confidence sequences, reducing 99.7% user exposure risk in Netflix experiments.

Dae Woong Ham, Iavor Bojinov, Michael Lindon et al.

ProtoVAE is a variational autoencoder-based self-explainable prototype model achieving high accuracy and trustworthy explanations.

Srishti Gautam, Ahcene Boubekki, Stine Hansen et al.

Proposes weakly-supervised multi-granularity map learning, boosting indoor navigation success rate by 4%, through detailed environment representation and object localization.

Peihao Chen, Dongyu Ji, Kunyang Lin et al.

ToupleGDD integrates three coupled GNNs with DDQN to optimize influence maximization on large networks, achieving performance close to IMM.

Tiantian Chen, Siwen Yan, Jianxiong Guo et al.

MEMIT mass-edits 10,000 facts in GPT-J, reaching an 85.8 COUNTERFACT editing score at scale.

Kevin Meng, Arnab Sen Sharma, Alex Andonian et al.

PDEBENCH benchmarks 11 PDE types with FNO, U-Net, PINN, using multi-metric evaluation for physics-informed modeling.

Makoto Takamoto, Timothy Praditia, Raphael Leiteritz et al.

Introduces Subequivariant Graph Neural Network, improving physical dynamics prediction accuracy by over 3%.

Jiaqi Han, Wenbing Huang, Hengbo Ma et al.

This study investigates GPT-3's few-shot table reasoning ability, leveraging Chain of Thoughts prompts to achieve near state-of-the-art performance.

Wenhu Chen

Derived exact high-dimensional asymptotics for stochastic gradient methods (SGD, momentum, Langevin) via discrete DMFT equations, validated numerically.

Cedric Gerbelot, Emanuele Troiani, Francesca Mignacco et al.

RankT5 fine-tunes T5 with ranking losses, improving ranking performance by 1.8% on MS MARCO dataset.

Honglei Zhuang, Zhen Qin, Rolf Jagerman et al.

CTL++ dataset tests neural networks' systematic generalization on unseen function compositions; transformers struggle significantly, with accuracy dropping below 30% in out-of-distribution tests.

Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber

ERNIE-Layout enhances pre-training with layout knowledge, achieving significant improvements in document understanding tasks.

Qiming Peng, Yinxu Pan, Wenjin Wang et al.

Using symmetry analysis, proves over-parameterization turns spurious minima into saddles, facilitating gradient optimization.

Yossi Arjevani, Michael Field

RING++ uses roto-translation invariant features for global localization on sparse LiDAR scans, ensuring global convergence without learning, outperforming state-of-the-art methods.

Xuecheng Xu, Sha Lu, Jun Wu et al.

Based on 172 papers, proposes a five-category sociotechnical harm taxonomy to systematically identify potential algorithmic harms.

Renee Shelby, Shalaleh Rismani, Kathryn Henne et al.

VLMaps fuses pretrained visual-language features with 3D reconstruction for precise spatial open-vocabulary navigation.

Chenguang Huang, Oier Mees, Andy Zeng et al.