Proposes a random-initialized single-step PGD method for fast adversarial training, extending to Euclidean norm, reducing training time while maintaining robustness and interpretability.

Justin Goodwin, Olivia Brown, Victoria Helus

Proposed a three-stage framework using scene context for long-term human motion prediction, significantly improving accuracy.

Zhe Cao, Hang Gao, Karttikeya Mangalam et al.

INT benchmark evaluates generalization in theorem proving using inequalities; MCTS enhances proving new theorems.

Yuhuai Wu, Albert Qiaochu Jiang, Jimmy Ba et al.

This paper introduces LaBSE, a multilingual sentence embedding model combining MLM, TLM, dual encoders, and additive margin softmax, achieving 83.7% accuracy across 112 languages.

Fangxiaoyu Feng, Yinfei Yang, Daniel Cer et al.

AGE framework excels in node clustering and link prediction using adaptive encoding and Laplacian smoothing.

Ganqu Cui, Jie Zhou, Cheng Yang et al.

Proposes a contrastive framework for multimodal VAEs, leveraging PMI differences to improve data efficiency and sample distinction, validated on MNIST-SVHN and CUB datasets.

Yuge Shi, Brooks Paige, Philip H. S. Torr et al.

DAPPLE combines data and pipeline parallelism with topology-aware scheduling, achieving up to 3.23× speedup and 12% memory reduction in large model training.

Shiqing Fan, Yi Rong, Chen Meng et al.

Proposes that deep discriminative models are linearly identifiable in function space, validated on GPT-2, BERT, and simulated data, using nonlinear ICA theory.

Geoffrey Roeder, Luke Metz, Diederik P. Kingma

Proposed a robust linear regression model for noisy network data, achieving significant accuracy and inference improvements.

Can M. Le, Tianxi Li

Swapping Autoencoder enables efficient image editing by encoding structure and texture, improving generation quality and speed.

Taesung Park, Jun-Yan Zhu, Oliver Wang et al.

Proposed Goal-Oriented Semantic Exploration system combines explicit semantic maps and reinforcement learning, achieving 54.4% success in unseen environments, outperforming baselines.

Devendra Singh Chaplot, Dhiraj Gandhi, Abhinav Gupta et al.

Proposes graph-based Path Reasoning (CPR) for conversational recommendation, explicitly leveraging user attributes, outperforming SOTA EAR and CRM by 15-20% on success rate.

Wenqiang Lei, Gangyi Zhang, Xiangnan He et al.

GShard combines conditional computation and automatic sharding to train a 600-billion-parameter multilingual Transformer efficiently, reducing costs and boosting performance.

Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu et al.

Proposes linear attention reducing Transformer complexity from O(N²) to O(N), enabling fast long-sequence autoregressive inference.

Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas et al.

Proposes inverse module transfer with Bayesian optimization to guarantee positive transfer in robotics, validated on quadrotors.

Michael J. Sorocky, Siqi Zhou, Angela P. Schoellig

Using optimal transport plans to build transfer operators for coherent set detection, enhanced by regularization for noise robustness.

Péter Koltai, Johannes von Lindheim, Sebastian Neumayer et al.

AutoCTR employs evolutionary algorithms and learning-to-rank guidance to automatically discover neural interaction architectures for CTR prediction.

Qingquan Song, Dehua Cheng, Hanning Zhou et al.

Using fSIM-NET to predict 3D object functionality, complemented by iGEN-NET for interaction scene generation.

Ruizhen Hu, Zihao Yan, Jingwen Zhang et al.

Deep generative models (VAE + regressor) enable efficient microstructure design and multiscale system assembly with continuous latent spaces, improving diversity and compatibility.

Liwei Wang, Yu-Chin Chan, Faez Ahmed et al.

Proposes a nearest-neighbor based gradient estimator with sharp nonasymptotic bounds, applicable to dimension reduction, optimization, and disentanglement, outperforming existing methods.

Guillaume Ausset, Stephan Clémençon, François Portier