ICLR

Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning

Huiwon Jang, Hankook Lee, Jinwoo Shin

Comments Accepted to ICLR 2023 (Spotlight). The first two authors contributed equally. The code is available at https://github.com/alinlab/PsCo

Learning to Grow Pretrained Models for Efficient Transformer Training

Peihao Wang, Rameswar Panda, Lucas Torroba Hennigen, Philip Greengard, Leonid Karlinsky, Rogerio Feris, David Daniel Cox, Zhangyang Wang, Yoon Kim

Comments International Conference on Learning Representations (ICLR), 2023

Preference Transformer: Modeling Human Preferences using Transformers for RL

Changyeon Kim, Jongjin Park, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee

Comments Project website: https://sites.google.com/view/preference-transformer. Accepted to ICLR 2023

STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables

Jaehyun Nam, Jihoon Tack, Kyungmin Lee, Hankook Lee, Jinwoo Shin

Comments ICLR 2023 (Spotlight)

Discovering Evolution Strategies via Meta-Black-Box Optimization

Robert Tjarko Lange, Tom Schaul, Yutian Chen, Tom Zahavy, Valentin Dallibard, Chris Lu, Satinder Singh, Sebastian Flennerhag

Comments 25 pages, 21 figures

Journal ref 11th International Conference on Learning Representations, ICLR 2023

Interpretable Geometric Deep Learning via Learnable Randomness Injection

Siqi Miao, Yunan Luo, Mia Liu, Pan Li

Comments ICLR 2023

Protein Sequence and Structure Co-Design with Equivariant Translation

Chence Shi, Chuanrui Wang, Jiarui Lu, Bozitao Zhong, Jian Tang

Comments Published as a conference paper at ICLR 2023, see https://openreview.net/forum?id=pRCMXcfdihq

Scaling Forward Gradient With Local Losses

Mengye Ren, Simon Kornblith, Renjie Liao, Geoffrey Hinton

Comments 31 pages, ICLR 2023

Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought

Abulhair Saparov, He He

Comments Published as a conference paper at ICLR 2023

Information-Theoretic Analysis of Unsupervised Domain Adaptation

Ziqiao Wang, Yongyi Mao

Comments Accepted to ICLR 2023

GFlowNets and variational inference

Nikolay Malkin, Salem Lahlou, Tristan Deleu, Xu Ji, Edward Hu, Katie Everett, Dinghuai Zhang, Yoshua Bengio

Comments ICLR 2023 final version; code: https://github.com/GFNOrg/GFN_vs_HVI

3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation

Ho Hin Lee, Shunxing Bao, Yuankai Huo, Bennett A. Landman

Comments Accepted to ICLR 2023

Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning

Pan Lu, Liang Qiu, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, Tanmay Rajpurohit, Peter Clark, Ashwin Kalyan

Comments ICLR 2023. 26 pages and 18 figures. The data and code are available at https://promptpg.github.io

CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment

Hongwei Xue, Yuchong Sun, Bei Liu, Jianlong Fu, Ruihua Song, Houqiang Li, Jiebo Luo

Comments Accepted by ICLR 2023

Imbalanced Semi-supervised Learning with Bias Adaptive Classifier

Renzhen Wang, Xixi Jia, Quanziang Wang, Yichen Wu, Deyu Meng

Comments Accepted by ICLR 2023

Is Attention All That NeRF Needs?

Mukund Varma T, Peihao Wang, Xuxi Chen, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang

Comments International Conference on Learning Representations (ICLR), 2023

Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization

Yongqiang Chen, Kaiwen Zhou, Yatao Bian, Binghui Xie, Bingzhe Wu, Yonggang Zhang, Kaili Ma, Han Yang, Peilin Zhao, Bo Han, James Cheng

Comments ICLR 2023, 50 pages, 58 figures

The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation

Zihui Xue, Zhengqi Gao, Sucheng Ren, Hang Zhao

Comments Accepted by ICLR 2023 (top-5%). The first three authors contribute equally. Project website: https://zihuixue.github.io/MFH/index.html

On the Robustness of Safe Reinforcement Learning under Observational Perturbations

Zuxin Liu, Zijian Guo, Zhepeng Cen, Huan Zhang, Jie Tan, Bo Li, Ding Zhao

Comments Published at the 11th International Conference on Learning Representations (ICLR 2023). 30 pages, 5 figures, 8 tables

Masked Distillation with Receptive Tokens

Tao Huang, Yuan Zhang, Shan You, Fei Wang, Chen Qian, Jian Cao, Chang Xu

Comments ICLR 2023

TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation

Rongjie Huang, Jinglin Liu, Huadai Liu, Yi Ren, Lichao Zhang, Jinzheng He, Zhou Zhao

Comments Accpeted to ICLR 2023

DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training

Joya Chen, Kai Xu, Yuhui Wang, Yifei Cheng, Angela Yao

Comments ICLR 2023

Factorized Fourier Neural Operators

Alasdair Tran, Alexander Mathews, Lexing Xie, Cheng Soon Ong

Comments Published in The Eleventh International Conference on Learning Representations (2023). Code is available at https://github.com/alasdairtran/fourierflow

Towards the Generalization of Contrastive Self-Supervised Learning

Weiran Huang, Mingyang Yi, Xuyang Zhao, Zihao Jiang

Comments Accepted by ICLR 2023

On Pre-trained Language Models for Antibody

Danqing Wang, Fei Ye, Hao Zhou

Comments Accepted in ICLR 2023

Token Merging: Your ViT But Faster

Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Christoph Feichtenhofer, Judy Hoffman

Comments Accepted ICLR 2023 Oral (top 5%) [final v2]. This version includes stable diffusion experiments. See code at https://github.com/facebookresearch/ToMe

$Λ$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells

Sajad Movahedi, Melika Adabinejad, Ayyoob Imani, Arezou Keshavarz, Mostafa Dehghani, Azadeh Shakery, Babak N. Araabi

Comments Published as a conference paper at ICLR 2023

A Theory of Dynamic Benchmarks

Ali Shirali, Rediet Abebe, Moritz Hardt

Comments ICLR 2023 Version

Learning to Estimate Shapley Values with Vision Transformers

Ian Covert, Chanwoo Kim, Su-In Lee

Comments ICLR 2023 camera-ready

S-NeRF: Neural Radiance Fields for Street Views

Ziyang Xie, Junge Zhang, Wenye Li, Feihu Zhang, Li Zhang

Comments ICLR 2023