Proposes a plug-and-play acceleration framework for semi-supervised VOS leveraging compressed video motion vectors, achieving up to 3.5× speed-up with minimal accuracy loss.

Kai Xu, Angela Yao

Residual Log-likelihood Estimation (RLE) boosts human pose regression, achieving 12.4 mAP improvement on MSCOCO.

Jiefeng Li, Siyuan Bian, Ailing Zeng et al.

High-order degradation modeling and U-Net discriminator enable pure synthetic training of Real-ESRGAN, significantly improving real-world image super-resolution.

Xintao Wang, Liangbin Xie, Chao Dong et al.

Proposed grid-based implicit function GAN method significantly improves 3D shape generation quality.

Moritz Ibing, Isaak Lim, Leif Kobbelt

Proposes IV-based dynamic incentive mechanism to improve compliance and estimate treatment effects in multi-round settings.

Daniel Ngo, Logan Stapleton, Vasilis Syrgkanis et al.

NCAD combines representation learning and deep anomaly detection, achieving SOTA on univariate/multivariate time series with semi-supervised capability.

Chris U. Carmona, François-Xavier Aubet, Valentin Flunkert et al.

TAPEX learns a neural SQL executor from synthetic SQL-output pairs and sets SOTA on WikiSQL, WTQ, SQA, and TabFact.

Qian Liu, Bei Chen, Jiaqi Guo et al.

Distribution-free conformal prediction guarantees 90% coverage, adaptable to classification and regression tasks.

Anastasios N. Angelopoulos, Stephen Bates

Enhancing dialogue faithfulness with controllable features using GPT-2 and T5, improving objectivity and informativeness.

Hannah Rashkin, David Reitter, Gaurav Singh Tomar et al.

HDMapNet uses multi-modal sensor fusion for online high-definition map prediction, outperforming baselines by over 50%.

Qi Li, Yue Wang, Yilun Wang et al.

Proposes SPOC algorithm for document-topic estimation, with error rate growing logarithmically with dictionary size.

Olga Klopp, Maxim Panov, Suzanne Sigalla et al.

Codex, a GPT-based model fine-tuned on GitHub code, achieves 28.8% success on HumanEval, with 70.2% using 100 samples, significantly surpassing GPT-3.

Mark Chen, Jerry Tworek, Heewoo Jun et al.

This survey comprehensively reviews recent advances in dialogue summarization, including datasets, models, and future directions, emphasizing multi-domain and multi-modal techniques.

Xiachong Feng, Xiaocheng Feng, Bing Qin

Proposes fMBN-E, an ensemble method combining multiple MBN structures for unsupervised clustering, achieving state-of-the-art results with hundreds-fold speedup.

Xiao-Lei Zhang

Proposes Variational Diffusion Models (VDM) achieving state-of-the-art likelihoods on image density benchmarks by optimizing noise schedules and incorporating Fourier features.

Diederik P. Kingma, Tim Salimans, Ben Poole et al.

Distribution-free prediction bands for multivariate functional time series guarantee 95% coverage, applied to Italian gas market demand and supply curves.

Jacopo Diquigiovanni, Matteo Fontana, Simone Vantini

ASDiv dataset enhances math word problem solver evaluation accuracy through diverse lexicon and problem types.

Shen-Yun Miao, Chao-Chun Liang, Keh-Yih Su

LaSynth learns latent execution traces for synthesis, reaching 55.2% behavioral accuracy on restricted C, about 20 points above executor-free baselines.

Xinyun Chen, Dawn Song, Yuandong Tian

DNN-based gesture recognition combined with potential field algorithms enables intuitive drone swarm trajectory and formation control, with an average error of 5.6cm.

Valerii Serpiva, Ekaterina Karmanova, Aleksey Fedoseev et al.

Habitat 2.0 combines ReplicaCAD, high-speed physics simulation, and HAB benchmarks to advance long-horizon household robot tasks.

Andrew Szot, Alex Clegg, Eric Undersander et al.