Application Areas
34,437 papers (4 classified directly here)
Subtopics · a paper can sit in several, so these overlap
Domain Adaptation (9,897)
Efficient Computing (8,226)
Data Augmentation (3,648)
Fairness (3,574)
Knowledge Distillation (3,219)
Privacy (3,022)
Domain Generalization (1,972)
Model Compression (1,736)
Risk Management (1,119)
Model Merging (592)
Recommender Systems (343)
Information Retrieval (249)
Text Classification (144)
Text Processing (2)
Papers per year
1
3
5
5
4
19
24
28
26
35
42
55
142
116
147
330
517
1,020
1,828
2,498
3,411
3,854
5,063
6,422
7,176
1,666
2000
'5
'10
'15
'20
'25
Papers (including subtopics)
The “Problem” of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation
EMNLP 2022
The Rich Get Richer: Disparate Impact of Semi-Supervised Learning
ICLR 2022
The Role of Pretrained Representations for the OOD Generalization of RL Agents
ICLR 2022
The RoyalFlush System for the WMT 2022 Efficiency Task
EMNLP 2022
Theseus: A Library for Differentiable Nonlinear Optimization
NeurIPS 2022
The SPECTRANS System Description for the WMT22 Biomedical Task
EMNLP 2022
The State of Sparse Training in Deep Reinforcement Learning
ICML 2022
The subtle language of exclusion: Identifying the Toxic Speech of Trans-exclusionary Radical Feminists
NAACL 2022
The THUEE System Description for the IARPA OpenASR21 Challenge
Interspeech 2022
The Trade-offs of Domain Adaptation for Neural Language Models
ACL 2022
The trade-offs of model size in large recommendation models : 100GB to 10MB Criteo-tb DLRM model
NeurIPS 2022
The Two Dimensions of Worst-Case Training and Their Integrated Effect for Out-of-Domain Generalization
CVPR 2022
The Undesirable Dependence on Frequency of Gender Bias Metrics Based on Word Embeddings
EMNLP 2022
The (Undesired) Attenuation of Human Biases by Multilinguality
EMNLP 2022
The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes
NeurIPS 2022
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training
ICLR 2022
The Unsurprising Effectiveness of Pre-Trained Vision Models for Control
ICML 2022
The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022
ACL 2022
THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption
ACL 2022
Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations
AISTATS 2022
Tiger: Disk-Adaptive Redundancy Without Placement Restrictions
OSDI 2022
Tight and Robust Private Mean Estimation with Few Users
ICML 2022
Tight Neural Network Verification via Semidefinite Relaxations and Linear Reformulations
AAAI 2022
Tile Networks: Learning Optimal Geometric Layout for Whole-page Recommendation
AISTATS 2022
Time Waits for No One! Analysis and Challenges of Temporal Misalignment
NAACL 2022