Papers
32 papers found
Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again
Xin-Chun Li, Wen-shu Fan, Shaoming Song et al.
What Makes a "Good" Data Augmentation in Knowledge Distillation - A Statistical Perspective
Huan Wang, Suhas Lohit, Michael N. Jones et al.
What Makes Graph Neural Networks Miscalibrated?
Hans Hao-Hsun Hsu, Yuesong Shen, Christian Tomani et al.
Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier
Youngjo Lee, Hongje Seong, Euntai Kim
Imputing Out-of-Vocabulary Embeddings with LOVE Makes LanguageModels Robust with Little Cost
Lihu Chen, Gael Varoquaux, Fabian Suchanek
What Makes Reading Comprehension Questions Difficult?
Saku Sugawara, Nikita Nangia, Alex Warstadt et al.
Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions
Haw-Shiuan Chang, Andrew McCallum
Deduplicating Training Data Makes Language Models Better
Katherine Lee, Daphne Ippolito, Andrew Nystrom et al.
What Makes Good In-Context Examples for GPT-3?
Jiachang Liu, Dinghan Shen, Yizhe Zhang et al.
AS-IntroVAE: Adversarial Similarity Distance Makes
Robust IntroVAE
Lu Changjie, Zheng Shen, Wang Zirui et al.
Layer or Representation Space: What Makes BERT-based Evaluation Metrics Robust?
Doan Nam Long Vu, Nafise Sadat Moosavi, Steffen Eger
Zhegu@SMM4H-2022: The Pre-training Tweet & Claim Matching Makes Your Prediction Better
Pan He, Chen YuZe, Yanru Zhang
What Makes Transfer Learning Work for Medical Images: Feature Reuse & Other Factors
Christos Matsoukas, Johan Fredin Haslum, Moein Sorkhei et al.
Decoupling Makes Weakly Supervised Local Feature Better
Kunhong Li, Longguang Wang, Li Liu et al.
Convolutional Embedding Makes Hierarchical Vision Transformer Stronger
Cong Wang, Hongmin Xu, Xiong Zhang et al.
What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment
Matthew Finlayson, Kyle Richardson, Ashish Sabharwal et al.
Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive Translators
Xinyou Wang, Zaixiang Zheng, Shujian Huang
Parameter-Efficient Tuning Makes a Good Classification Head
Zhuoyi Yang, Ming Ding, Yanhui Guo et al.
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
Sewon Min, Xinxi Lyu, Ari Holtzman et al.
What Makes Data-to-Text Generation Hard for Pretrained Language Models?
Moniba Keymanesh, Adrian Benton, Mark Dredze
What Makes Better Augmentation Strategies? Augment Difficult but Not too Different
Jaehyung Kim, Dongyeop Kang, Sungsoo Ahn et al.
Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
Ningyu Zhang, Luoqiu Li, Xiang Chen et al.
Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning
Philippe Hansen-Estruch, Amy Zhang, Ashvin Nair et al.
Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)
Yu Huang, Junyang Lin, Chang Zhou et al.
Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks
Franco Pellegrini, Giulio Biroli