This paper evaluates adapter-based tuning for pretrained language models, showing superior performance in low-resource and cross-lingual tasks, with better regularization and robustness.

Ruidan He, Linlin Liu, Hai Ye et al.

Patch Slimming removes redundant ViT patches, cutting DeiT-Ti FLOPs by 53.8% with only a 0.1-point ImageNet Top-1 drop.

Yehui Tang, Kai Han, Yunhe Wang et al.

SketchGen uses Transformer-based sequence modeling to generate CAD sketches, outperforming state-of-the-art methods with improved distribution alignment.

Wamiq Reyaz Para, Shariq Farooq Bhat, Paul Guerrero et al.

An ICNN benchmark shows that tW2s best recovers high-dimensional W2 maps, yet OT accuracy does not guarantee better generation.

Alexander Korotin, Lingxiao Li, Aude Genevay et al.

This book systematically covers convex analysis, duality, and numerical methods like interior-point algorithms, emphasizing robust optimization and cone programming with practical examples.

Evgeniya Vorontsova, Roland Hildebrand, Alexander Gasnikov et al.

Proposes FedNCF, extending Neural Collaborative Filtering to federated learning with secure aggregation, achieving comparable accuracy and faster convergence.

Vasileios Perifanis, Pavlos S. Efraimidis

This study evaluates the relationship between perplexity and human-like reading behavior across Japanese and English, revealing language-specific differences.

Tatsuki Kuribayashi, Yohei Oseki, Takumi Ito et al.

Proposes Cross Pseudo Supervision (CPS) for semi-supervised semantic segmentation, achieving state-of-the-art results on Cityscapes and PASCAL VOC 2012.

Xiaokang Chen, Yuhui Yuan, Gang Zeng et al.

Proposes adaptive conformal inference (ACI) to maintain coverage under distribution shifts, validated on real datasets with robust results.

Isaac Gibbs, Emmanuel Candès

Proposes Galerkin Transformer with softmax-free attention, grounded in Petrov-Galerkin theory, improving PDE operator learning efficiency.

Shuhao Cao

Using mean-field and continuous limits, the paper proves that deep ResNets with infinite width and depth converge to zero loss via PDE analysis, providing theoretical insight into overparameterization.

Zhiyan Ding, Shi Chen, Qin Li et al.

Proposes a policy gradient algorithm for multi-objective nonlinear concave optimization with sample complexity O(M^4σ^2/(1-γ)^8ε^4), ensuring global convergence.

Qinbo Bai, Mridul Agarwal, Vaneet Aggarwal

SEM-TAB-FACTS introduces a new dataset and tasks for fact verification in scientific tables, featuring 180K+ statements and 16M+ evidence annotations.

Nancy X. R. Wang, Diwakar Mahajan, Marina Danilevsky et al.

ByT5, a Transformer-based byte-level pre-trained model, matches token-based performance, improves robustness, with five model sizes and innovative training strategies.

Linting Xue, Aditya Barua, Noah Constant et al.

AIM leverages Wasserstein-1 distance with a goal-specific quasimetric to efficiently guide goal-conditioned reinforcement learning, accelerating convergence by ~50%.

Ishan Durugkar, Mauricio Tec, Scott Niekum et al.

DiSECt: a fully differentiable FEM-based soft material cutting simulator with continuous contact and damage models, enabling efficient parameter calibration and control optimization.

Eric Heiden, Miles Macklin, Yashraj Narang et al.

Proposes UNICORN, a graph-based RL framework, significantly improving CRS success rate by 12% and reducing dialogue turns by 20%.

Yang Deng, Yaliang Li, Fei Sun et al.

KLUE constructs 8 Korean NLU tasks, using from-scratch data collection and pretrained models KLUE-BERT and KLUE-RoBERTa, outperforming multilingual and open-source baselines.

Sungjoon Park, Jihyung Moon, Sungdong Kim et al.

Proposes two methods: failure diagnosis via parameter deviation search and synthetic experience correction, boosting robot grasp success rate from 40% to over 60%.

Alex Mitrevski, Paul G. Plöger, Gerhard Lakemeyer

Proposes Exemplar-Based Open-Set Panoptic Segmentation Network (EOPSN), achieving 37.7% PQ on COCO with unknown class detection, advancing open-world scene understanding.

Jaedong Hwang, Seoung Wug Oh, Joon-Young Lee et al.