Issues
- 15
[2000] Maximum Entropy Markov Models for Information Extraction and Segmentation [paper-reading]
#23 opened by yoheikikuta - 14
[2204.06125] Hierarchical Text-Conditional Image Generation with CLIP Latents [paper-reading]
#65 opened by yoheikikuta - 8
[2202.05240] ChemicalX: A Deep Learning Library for Drug Pair Scoring [paper-reading]
#64 opened by yoheikikuta - 10
[2112.10741] GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models [paper-reading]
#63 opened by yoheikikuta - 14
- 12
[2104.08691] The Power of Scale for Parameter-Efficient Prompt Tuning [paper-reading]
#59 opened by yoheikikuta - 9
[2010.11929] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale [paper-reading]
#56 opened by yoheikikuta - 19
[1910.10683] Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer [paper-reading]
#55 opened by yoheikikuta - 15
[2006.01245] An Effectiveness Metric for Ordinal Classification: Formal Properties and Experimental Results [paper-reading]
#54 opened by yoheikikuta - 11
[2004.10964] Don't Stop Pretraining: Adapt Language Models to Domains and Tasks [paper-reading]
#53 opened by yoheikikuta - 11
- 8
[2019] A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis [paper-reading]
#51 opened by yoheikikuta - 12
[1908.03265] On the Variance of the Adaptive Learning Rate and Beyond [paper-reading]
#50 opened by yoheikikuta - 11
[1810.00740] Improving the Generalization of Adversarial Training with Domain Adaptation [paper-reading]
#49 opened by yoheikikuta - 11
[1808.02651] Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer [paper-reading]
#48 opened by yoheikikuta - 10
[1905.11946] EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks [paper-reading]
#47 opened by yoheikikuta - 11
[1906.07132] Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA [paper-reading]
#44 opened by yoheikikuta - 12
[1906.02443] Robust Neural Machine Translation with Doubly Adversarial Inputs [paper-reading]
#43 opened by yoheikikuta - 10
[2007.06174] Generating Fluent Adversarial Examples for Natural Languages [paper-reading]
#42 opened by yoheikikuta - 11
[2019] Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency [paper-reading]
#41 opened by yoheikikuta - 10
[1907.00208] Deep Gamblers: Learning to Abstain with Portfolio Theory [paper-reading]
#40 opened by yoheikikuta - 10
[1909.11942] ALBERT: A Lite BERT for Self-supervised Learning of Language Representations [paper-reading]
#38 opened by yoheikikuta - 10
[1902.03245] Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegability [paper-reading]
#37 opened by yoheikikuta - 10
[1909.03186] On Extractive and Abstractive Neural Document Summarization with Transformer Language Models [paper-reading]
#34 opened by yoheikikuta - 10
[1904.00759] Adversarial camera stickers: A physical camera-based attack on deep learning systems [paper-reading]
#33 opened by yoheikikuta - 10
[1905.10964] Combating Label Noise in Deep Learning Using Abstention [paper-reading]
#32 opened by yoheikikuta - 9
[1907.11692] RoBERTa: A Robustly Optimized BERT Pretraining Approach [paper-reading]
#31 opened by yoheikikuta - 8
[1901.02860] Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context [paper-reading]
#30 opened by yoheikikuta - 13
- 9
- 11
[1703.00810] Opening the Black Box of Deep Neural Networks via Information [paper-reading]
#27 opened by yoheikikuta - 11
[1503.02406] Deep Learning and the Information Bottleneck Principle [paper-reading]
#26 opened by yoheikikuta - 11
[1801.07698] ArcFace: Additive Angular Margin Loss for Deep Face Recognition [paper-reading]
#24 opened by yoheikikuta - 13
- 11
[1508.07909] Neural Machine Translation of Rare Words with Subword Units [paper-reading]
#20 opened by yoheikikuta - 10
- 14
[1810.04805] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding [paper-reading]
#18 opened by yoheikikuta - 12
[1802.03888] Consistent Individualized Feature Attribution for Tree Ensembles [paper-reading]
#17 opened by yoheikikuta - 14
[1606.05340] Exponential expressivity in deep neural networks through transient chaos [paper-reading]
#16 opened by yoheikikuta - 10
[2021] Mitigating Confounding Bias in Recommendation via Information Bottleneck
#61 opened by yoheikikuta - 18
- 9
[1909.08423] Deep neural network solution of the electronic Schrodinger equation
#58 opened by yoheikikuta - 12
[2019] Hamiltonian Neural Networks
#46 opened by yoheikikuta - 12
[2019] Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
#45 opened by yoheikikuta - 9
[2019] When Does Label Smoothing Help?
#39 opened by yoheikikuta - 13
- 13
- 13
[2001] Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
#25 opened by yoheikikuta - 13
[2021] Learning Transferable Visual Models From Natural Language Supervision
#57 opened by yoheikikuta - 10
[2018] GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training
#22 opened by yoheikikuta