ICLR

A General Framework for User-Guided Bayesian Optimization

Carl Hvarfner, Frank Hutter, Luigi Nardi

Comments 18 pages, 11 figures

Journal ref 12:th International Conference on Learning Representations (ICLR 2024)

Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions

Taehyeon Kim, Joonkee Kim, Gihun Lee, Se-Young Yun

Comments ICLR 2024 (Spotlight)

On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning

Rohan Subramani, Marcus Williams, Max Heitmann, Halfdan Holm, Charlie Griffin, Joar Skalse

Comments Published as a conference paper at ICLR 2024

Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis

Kai Chen, Chunwei Wang, Kuo Yang, Jianhua Han, Lanqing Hong, Fei Mi, Hang Xu, Zhengying Liu, Wenyong Huang, Zhenguo Li, Dit-Yan Yeung, Lifeng Shang, Xin Jiang, Qun Liu

Comments Accepted by ICLR 2024

DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

Zhengxiang Shi, Aldo Lipani

Comments ICLR 2024. Code is available at https://github.com/ZhengxiangShi/DePT

Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions

Chinmay Rane, Kanishka Tyagi, Michael Manry

Comments Tiny ICLR Approved

GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation

Kai Chen, Enze Xie, Zhe Chen, Yibo Wang, Lanqing Hong, Zhenguo Li, Dit-Yan Yeung

Comments Accept by ICLR 2024. Project Page: https://kaichen1998.github.io/projects/geodiffusion/

Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?

Jianfei Yang, Hanjie Qian, Yuecong Xu, Kai Wang, Lihua Xie

Comments To be published at ICLR 2024, update formula and appendix, project and code available at https://sleepyseal.github.io/TransferScoreWeb/

Learning Disentangled Audio Representations through Controlled Synthesis

Yusuf Brima, Ulf Krumnack, Simone Pika, Gunther Heidemann

Comments 12 pages, 12 figures, accepted as a Tiny paper at ICLR 2024

Parametric Augmentation for Time Series Contrastive Learning

Xu Zheng, Tianchun Wang, Wei Cheng, Aitian Ma, Haifeng Chen, Mo Sha, Dongsheng Luo

Comments Accepted by International Conference on Learning Representations (ICLR 2024)

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems

Juno Kim, Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki

Comments ICLR 2024 spotlight

Quasi-Monte Carlo for 3D Sliced Wasserstein

Khai Nguyen, Nicola Bariletto, Nhat Ho

Comments Accepted to ICLR 2024 (Spotlight), 25 pages, 13 figures, 6 tables

CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting

Wang Xue, Tian Zhou, Qingsong Wen, Jinyang Gao, Bolin Ding, Rong Jin

Comments ICLR 2024

Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks

Federico Errica, Mathias Niepert

Comments The 12th International Conference on Learning Representations (ICLR 2024)

Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community

Arman Isajanyan, Artur Shatveryan, David Kocharyan, Zhangyang Wang, Humphrey Shi

Comments 16 pages with 10 figures, accepted at ICLR 2024 as a spotlight, codes can be accessed at https://github.com/Picsart-AI-Research/Social-Reward

Out-Of-Domain Unlabeled Data Improves Generalization

Amir Hossein Saberi, Amir Najafi, Alireza Heidari, Mohammad Hosein Movasaghinia, Abolfazl Motahari, Babak H. Khalaj

Comments Published at ICLR 2024 (Spotlight), 29 pages, no figures

Structure by Architecture: Structured Representations without Regularization

Felix Leeb, Guilia Lanzillotta, Yashas Annadani, Michel Besserve, Stefan Bauer, Bernhard Schölkopf

Comments Published at ICLR 2023

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency

Yannis Kalantidis, Mert Bülent Sarıyıldız, Rafael S. Rezende, Philippe Weinzaepfel, Diane Larlus, Gabriela Csurka

Comments Accepted at ICLR 2024. Project Page: https://europe.naverlabs.com/ret4loc

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Guowei Xu, Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé, Furong Huang, Huazhe Xu

Comments Accepted at The Twelfth International Conference on Learning Representations (ICLR 2024)

Intriguing properties of generative classifiers

Priyank Jaini, Kevin Clark, Robert Geirhos

Comments ICLR 2024 Spotlight

On the Limitations of Temperature Scaling for Distributions with Overlaps

Muthu Chidambaram, Rong Ge

Comments 27 pages, 9 Figures, published in ICLR 2024

Approximately Piecewise E(3) Equivariant Point Networks

Matan Atzmon, Jiahui Huang, Francis Williams, Or Litany

Comments ICLR 2024

NfgTransformer: Equivariant Representation Learning for Normal-form Games

Siqi Liu, Luke Marris, Georgios Piliouras, Ian Gemp, Nicolas Heess

Comments Published at ICLR 2024. Open-sourced at https://github.com/google-deepmind/nfg_transformer

Uncertainty Quantification via Stable Distribution Propagation

Felix Petersen, Aashwin Mishra, Hilde Kuehne, Christian Borgelt, Oliver Deussen, Mikhail Yurochkin

Comments Published at ICLR 2024, Code @ https://github.com/Felix-Petersen/distprop

LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents

Jae-Woo Choi, Youngwoo Yoon, Hyobin Ong, Jaehong Kim, Minsu Jang

Comments ICLR 2024. Code: https://github.com/lbaa2022/LLMTaskPlanning

Refined Direct Preference Optimization with Synthetic Data for Behavioral Alignment of LLMs

Víctor Gallego

Comments Pre-print. Submitted to the ICLR 2024 Workshop on Representational Alignment (Re-Align)

Towards Meta-Pruning via Optimal Transport

Alexander Theus, Olin Geimer, Friedrich Wicke, Thomas Hofmann, Sotiris Anagnostidis, Sidak Pal Singh

Comments Accepted as a Spotlight (top 5% of submissions) at the International Conference on Learning Representations (ICLR) 2024

CABINET: Content Relevance based Noise Reduction for Table Question Answering

Sohan Patnaik, Heril Changwal, Milan Aggarwal, Sumit Bhatia, Yaman Kumar, Balaji Krishnamurthy

Comments Accepted at ICLR 2024 (spotlight)

Robust Angular Synchronization via Directed Graph Neural Networks

Yixuan He, Gesine Reinert, David Wipf, Mihai Cucuringu

Comments 9 pages for main text, ICLR 2024

Zero-Shot Robustification of Zero-Shot Models

Dyah Adila, Changho Shin, Linrong Cai, Frederic Sala

Comments International Conference on Learning Representations (ICLR), 2024