Supervision Complexity and its Role in Knowledge Distillation
Comments Published at ICLR 2023
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Leveraging Importance Weights in Subset Selection
Comments ICLR 2023
Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness
Comments ICLR 2023
Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions
Comments 19 pages, 7 figures, accepted by ICLR 2023
Mega: Moving Average Equipped Gated Attention
Comments Accepted by ICLR 2023. Final version (updating MT results). 13 pages, 4 figures and 7 tables
MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
Comments Accepted to ICLR 2023 as Spotlight Presentation. Code&demos: https://github.com/hustvl/MapTR
Don't overfit the history -- Recursive time series data augmentation
Comments Accepted to ICLR 2023 Resubmitted here due to major change in proofs following conference submission
Spherical Sliced-Wasserstein
Comments Published as a conference paper at ICLR 2023
Learning Locality and Isotropy in Dialogue Modeling
Comments To appear in ICLR 2023
Masked Image Modeling with Denoising Contrast
Comments Accepted by ICLR 2023. The code will be available at https://github.com/TencentARC/ConMIM
KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP
Comments Accepted by ICLR 2023 main track at https://openreview.net/forum?id=2nocgE1m0A
Sparse Mixture-of-Experts are Domain Generalizable Learners
Comments ICLR 2023 (accepted as Oral presentation)
Generate rather than Retrieve: Large Language Models are Strong Context Generators
Comments Accepted at ICLR 2023 (v3, add code and implementation details)
User-Interactive Offline Reinforcement Learning
Comments Accepted at ICLR 2023 - 11th International Conference on Learning Representations
Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding
Comments Accepted at ICLR 2023. The code is available at https://github.com/ajhamdi/vointcloud
Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
Comments Accepted by ICLR 2022
Transformer-Patcher: One Mistake worth One Neuron
Comments accepted in ICLR 2023
The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image
Comments Accepted at ICLR'23. Webpage: https://single-image-distill.github.io/, code: https://github.com/yukimasano/single-img-extrapolating
Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference
Comments 15 pages, 10 figures, 11 tables. Accepted as a conference paper at ICLR 2023
SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models
Comments Accepted by ICLR 2023. Project page: https://slotformer.github.io/
Estimating individual treatment effects under unobserved confounding using binary instruments
Comments Accepted at ICLR 2023
Concept-level Debugging of Part-Prototype Networks
Comments Accepted for publication at ICLR 2023
Critic Sequential Monte Carlo
Comments ICLR 2023
Linear Connectivity Reveals Generalization Strategies
Comments Publushed as a conference paper at ICLR 2023
Continuous-time identification of dynamic state-space models by deep subspace encoding
Comments Accepted to ICLR 2023
FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning
Comments Accepted at ICLR 2022
Modeling Uncertain Feature Representation for Domain Generalization
Comments This work is an extension of our ICLR 2022 paper [arXiv:2202.03958] https://openreview.net/forum?id=6HN7LHyzGgC
Critical Points in Quantum Generative Models
Journal ref International Conference on Learning Representations (2022)
Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage
Comments We changed the title from the first version. This is a longer version of the article accepted in ICLR 2022. The following things are added (1) a new algorithm CPPO-LR where the constraint is given in a log-likelihood form, (2) how to instantiate CPPO on (nonparametric) linear MDPs, (3) posterior sampling in a model-free way
StarGraph: Knowledge Representation Learning based on Incomplete Two-hop Subgraph
Comments Under review in ICLR 2023 (https://openreview.net/forum?id=mTOB_VK_BWk)
