Proposes a compression-based macro discovery framework that extracts, evaluates, and diversifies action sequences to accelerate RL learning in related tasks.

Francisco M. Garcia, Bruno C. da Silva, Philip S. Thomas

Proposes SplineCNN with continuous B-spline kernels for fast geometric deep learning.

Matthias Fey, Jan Eric Lenssen, Frank Weichert et al.

Proposes Temporal Relation Network (TRN) for multi-scale temporal reasoning, boosting activity recognition accuracy by over 20% on key datasets.

Bolei Zhou, Alex Andonian, Aude Oliva et al.

Leveraging temporal word embeddings to quantify a century of gender and ethnic stereotypes in the US, validated against Census data.

Nikhil Garg, Londa Schiebinger, Dan Jurafsky et al.

OSQP: An operator splitting solver for quadratic programs, combining robustness and efficiency.

Bartolomeo Stellato, Goran Banjac, Paul Goulart et al.

UnFlow uses bidirectional Census loss for unsupervised optical flow learning, outperforming supervised methods on KITTI.

Simon Meister, Junhwa Hur, Stefan Roth

Proposes a differentiable mesh renderer with approximate gradients, enabling single-image 3D mesh reconstruction and editing using 2D supervision.

Hiroharu Kato, Yoshitaka Ushiku, Tatsuya Harada

Proposes locally-balanced MCMC proposals for discrete spaces, achieving significant efficiency gains and theoretical optimality.

Giacomo Zanella

Optimization-based control for 1:43 RC cars using receding horizon NMPC and contouring control, achieving 50Hz real-time operation.

Alexander Liniger, Alexander Domahidi, Manfred Morari

Introduced Matterport3D-based vision-language navigation framework using Seq2Seq, achieving 62.7% success in real indoor environments.

Peter Anderson, Qi Wu, Damien Teney et al.

Introduces bi-stochastic kernels for diffusion processes on manifolds, deriving their infinitesimal generators and heat kernel connections, with spectral and Nyström analysis.

Nicholas F. Marshall, Ronald R. Coifman

Proposes eATE estimator for unknown interference, proving consistency under limited interference conditions.

Fredrik Sävje, Peter M. Aronow, Michael G. Hudgens

Mathematical proof of perception-distortion tradeoff; GANs approach the boundary; new evaluation framework proposed.

Yochai Blau, Tomer Michaeli

Relation Network (RN) learns deep relation metrics for few-shot classification, achieving state-of-the-art results without fine-tuning.

Flood Sung, Yongxin Yang, Li Zhang et al.

Proposed a novel CNN architecture for improving dense monocular reconstruction through deeply supervised feature learning.

Chamara Saroj Weerasekera, Ravi Garg, Yasir Latif et al.

NISP propagates final response importance scores for global neuron pruning, achieving significant speedups and compression with minimal accuracy loss.

Ruichi Yu, Ang Li, Chun-Fu Chen et al.

Proposes structured subgroup fairness auditing and learning algorithms based on weak agnostic learning, addressing fairness gerrymandering.

Michael Kearns, Seth Neel, Aaron Roth et al.

Proposes NARM, combining attention and sequence encoding, achieving significant improvements in long session recommendations.

Jing Li, Pengjie Ren, Zhumin Chen et al.

SQLNet uses dependency graphs to avoid order sensitivity, improving WikiSQL accuracy by 9-13%.

Xiaojun Xu, Chang Liu, Dawn Song

FTSum model reduces fake fact generation by 80% using dual-attention mechanism.

Ziqiang Cao, Furu Wei, Wenjie Li et al.