AR-LSAT combines Transformer and symbolic reasoning, revealing deep reasoning gaps in current models with accuracy below 35%. ARM achieves 65%, still behind humans.

Wanjun Zhong, Siyuan Wang, Duyu Tang et al.

Addresses few-shot image generation overfitting with cross-domain distance consistency loss and anchor strategy.

Utkarsh Ojha, Yijun Li, Jingwan Lu et al.

QA-GNN combines relevance scoring and joint graph reasoning, outperforming LM+KG models with 4.7% improvement on CommonsenseQA.

Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut et al.

Introduces MultiModalQA dataset with 29,918 questions requiring joint reasoning over text, tables, and images; ImplicitDecomp outperforms baselines with 51.7 F1.

Alon Talmor, Ori Yoran, Amnon Catav et al.

Query-based multi-domain meeting summarization with locate-then-summarize framework; QMSum dataset highlights challenges in long meeting understanding.

Ming Zhong, Da Yin, Tao Yu et al.

SpartQA enhances spatial reasoning in language models using distant supervision, significantly boosting performance on bAbI and boolQ datasets.

Roshanak Mirzaee, Hossein Rajaby Faghihi, Qiang Ning et al.

Introduced StylePTB, a large-scale benchmark with 21 fine-grained style changes, advancing controllable text style transfer research.

Yiwei Lyu, Paul Pu Liang, Hai Pham et al.

Proposes Traffic Transformer, using multi-head attention to dynamically learn spatial-temporal traffic features, greatly improving long-term prediction accuracy.

Haoyang Yan, Xiaolei Ma

Meta-tuning on combined datasets boosts large model zero-shot classification by 6.3% (220M to 770M params), surpassing prior SOTA.

Ruiqi Zhong, Kristy Lee, Zheng Zhang et al.

ReCo introduces regional contrastive learning for semantic segmentation, achieving high performance with only 5 labeled examples per class.

Shikun Liu, Shuaifeng Zhi, Edward Johns et al.

Introduced Field Convolution for surface CNNs, achieving state-of-the-art accuracy in geometry processing tasks.

Thomas W. Mitchel, Vladimir G. Kim, Michael Kazhdan

Introduces Point-Voxel Diffusion (PVD), combining diffusion models with point-voxel representation for high-fidelity 3D shape generation and multi-modal completion.

Linqi Zhou, Yilun Du, Jiajun Wu

Dynabench introduces a dynamic adversarial data collection platform, significantly reducing model error rates across four NLP tasks by leveraging multi-round human-model interactions.

Douwe Kiela, Max Bartolo, Yixin Nie et al.

By applying AlphaZero to Hex, the study reveals performance scales exponentially with board size and compute, enabling prediction of large-scale results from small experiments.

Andy L. Jones

HEPOS employs head-wise positional strides, reducing complexity and enabling processing of ten times longer documents for improved ROUGE scores.

Luyang Huang, Shuyang Cao, Nikolaus Parulian et al.

AST is the first convolution-free, attention-based model for audio classification, achieving 0.485 mAP on AudioSet.

Yuan Gong, Yu-An Chung, James Glass

Tactile-RL method achieves insertion of unknown geometry objects with over 85% success rate.

Siyuan Dong, Devesh K. Jha, Diego Romeres et al.

GPV-1 unifies vision tasks through language-conditioned shared heads, reaching 62.5 VQA and 1.023 CIDEr-D on COCO.

Tanmay Gupta, Amita Kamath, Aniruddha Kembhavi et al.

LoFTR employs Transformer-based dense pixel matching, excelling in low-texture areas without keypoint detection.

Jiaming Sun, Zehong Shen, Yuang Wang et al.

Proposes DietNeRF with semantic consistency loss for high-quality few-shot view synthesis from minimal images.

Ajay Jain, Matthew Tancik, Pieter Abbeel