ICLR - arXivDaily 期刊&会议

2104.04987 2024-03-06 cs.LG cs.AI

AutoGL: A Library for Automated Graph Learning

Ziwei Zhang, Yijian Qin, Zeyang Zhang, Chaoyu Guan, Jie Cai, Heng Chang, Jiyan Jiang, Haoyang Li, Zixin Sun, Beini Xie, Yang Yao, Yipeng Zhang, Xin Wang, Wenwu Zhu

Comments Extended version; initial version published at ICLR 2021 Workshop on Geometrical and Topological Representation Learning

2403.01832 2024-03-05 cs.AI cs.CL

Model-Based Data-Centric AI: Bridging the Divide Between Academic Ideals and Industrial Pragmatism

Chanjun Park, Minsoo Khang, Dahyun Kim

Comments Accepted for Data-centric Machine Learning Research (DMLR) Workshop at ICLR 2024

2401.15030 2024-03-05 cs.LG

On the generalization capacity of neural networks during generic multimodal reasoning

Takuya Ito, Soham Dan, Mattia Rigotti, James Kozloski, Murray Campbell

Comments ICLR 2024

2310.11142 2024-03-05 cs.CV cs.LG

BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference

Siqi Kou, Lei Gan, Dequan Wang, Chongxuan Li, Zhijie Deng

Comments ICLR 2024

2310.11053 2024-03-05 cs.CL cs.AI cs.CY

Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning

Shitong Duan, Xiaoyuan Yi, Peng Zhang, Tun Lu, Xing Xie, Ning Gu

Comments Accepted by ICLR 2024

2306.08018 2024-03-05 q-bio.QM cs.AI cs.CE cs.CL cs.IR cs.LG

Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models

Yin Fang, Xiaozhuan Liang, Ningyu Zhang, Kangwei Liu, Rui Huang, Zhuo Chen, Xiaohui Fan, Huajun Chen

Comments ICLR 2024. Project homepage: https://github.com/zjunlp/Mol-Instructions

2301.11259 2024-03-05 cs.LG cs.AI cs.CE cs.CL

Domain-Agnostic Molecular Generation with Chemical Feedback

Yin Fang, Ningyu Zhang, Zhuo Chen, Lingbing Guo, Xiaohui Fan, Huajun Chen

Comments ICLR 2024

2403.01599 2024-03-05 cs.CV cs.AI cs.CL cs.LG

SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos

Yulei Niu, Wenliang Guo, Long Chen, Xudong Lin, Shih-Fu Chang

Comments Accepted by ICLR 2024

2403.01431 2024-03-05 cs.CV

Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval

Yongchao Du, Min Wang, Wengang Zhou, Shuping Hui, Houqiang Li

Comments ICLR 2024 spotlight

2403.01412 2024-03-05 cs.CV eess.IV eess.SP

LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition

Lingfeng Liu, Dong Ni, Hangjie Yuan

Comments Accepted to ICLR 2024

2403.01400 2024-03-05 cs.LG cs.AI

Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks

Tianyu Fan, Lirong Wu, Yufei Huang, Haitao Lin, Cheng Tan, Zhangyang Gao, Stan Z. Li

Comments Published as a conference paper at ICLR 2024

2403.01189 2024-03-05 cs.LG cs.CV

Training Unbiased Diffusion Models From Biased Dataset

Yeongmin Kim, Byeonghu Na, Minsang Park, JoonHo Jang, Dongjun Kim, Wanmo Kang, Il-Chul Moon

Comments International Conference on Learning Representations (ICLR 2024)

2403.01058 2024-03-05 cs.CV cs.LG

Neural Field Classifiers via Target Encoding and Classification Loss

Xindi Yang, Zeke Xie, Xiong Zhou, Boyu Liu, Buhua Liu, Yi Liu, Haoran Wang, Yunfeng Cai, Mingming Sun

Comments ICLR 2024 Main Conference; 17 pages; 11 figures; 13 tables

2403.00871 2024-03-05 cs.CR cs.AI cs.CL cs.LG

Teach LLMs to Phish: Stealing Private Information from Language Models

Ashwinee Panda, Christopher A. Choquette-Choo, Zhengming Zhang, Yaoqing Yang, Prateek Mittal

Comments ICLR 2024

2312.11954 2024-03-05 cs.CV

Adversarial AutoMixup

Huafeng Qin, Xin Jin, Yun Jiang, Mounim A. El-Yacoubi, Xinbo Gao

Comments ICLR 2024 Camera Ready.(19 pages) with the source code at https://github.com/JinXins/Adversarial-AutoMixup

2312.01133 2024-03-05 stat.ML cs.LG

$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence

Juno Kim, Jaehyuk Kwon, Mincheol Cho, Hyunjong Lee, Joong-Ho Won

Comments ICLR 2024; 27 pages, 7 figures, 8 tables

2310.13822 2024-03-05 cs.LG

Adversarial Attacks on Fairness of Graph Neural Networks

Binchi Zhang, Yushun Dong, Chen Chen, Yada Zhu, Minnan Luo, Jundong Li

Comments Accepted at ICLR 2024

2310.07855 2024-03-05 cs.CV cs.LG

CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping

Tim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars

Comments ICLR 2024 (spotlight)

2310.06474 2024-03-05 cs.CL

Multilingual Jailbreak Challenges in Large Language Models

Yue Deng, Wenxuan Zhang, Sinno Jialin Pan, Lidong Bing

Comments ICLR 2024

2310.04418 2024-03-05 cs.LG

Functional Interpolation for Relative Positions Improves Long Context Transformers

Shanda Li, Chong You, Guru Guruganesh, Joshua Ainslie, Santiago Ontanon, Manzil Zaheer, Sumit Sanghai, Yiming Yang, Sanjiv Kumar, Srinadh Bhojanapalli

Comments 26 pages; ICLR 2024 camera ready version

2307.15337 2024-03-05 cs.CL cs.AI

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang

Comments In ICLR'24

2307.00494 2024-03-05 q-bio.BM cs.LG q-bio.QM stat.ML

Improving Protein Optimization with Smoothed Fitness Landscapes

Andrew Kirjner, Jason Yim, Raman Samusevich, Shahar Bracha, Tommi Jaakkola, Regina Barzilay, Ila Fiete

Comments ICLR 2024. Code: https://github.com/kirjner/GGS

2306.02010 2024-03-05 cs.LG

Memorization Capacity of Multi-Head Attention in Transformers

Sadegh Mahdavi, Renjie Liao, Christos Thrampoulidis

Comments ICLR 2024 (Spotlight)

2305.15086 2024-03-05 cs.CV cs.AI cs.LG stat.ML

Unpaired Image-to-Image Translation via Neural Schrödinger Bridge

Beomsu Kim, Gihyun Kwon, Kwanyoung Kim, Jong Chul Ye

Comments ICLR 2024

2304.14614 2024-03-05 cs.CV cs.CR

Fusion is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection

Zhiyuan Cheng, Hongjun Choi, James Liang, Shiwei Feng, Guanhong Tao, Dongfang Liu, Michael Zuzak, Xiangyu Zhang

Comments Accepted at ICLR'2024

2302.10970 2024-03-05 cs.CV

Differentiable Rendering with Reparameterized Volume Sampling

Nikita Morozov, Denis Rakitin, Oleg Desheulin, Dmitry Vetrov, Kirill Struminsky

Comments Accepted at AISTATS 2024. Short version of this paper appeared in ICLR 2023 Neural Fields workshop

2212.03827 2024-03-05 cs.CL cs.AI cs.LG

Discovering Latent Knowledge in Language Models Without Supervision

Collin Burns, Haotian Ye, Dan Klein, Jacob Steinhardt

Comments ICLR 2023

2403.00729 2024-03-04 cs.CV cs.RO

Can Transformers Capture Spatial Relations between Objects?

Chuan Wen, Dinesh Jayaraman, Yang Gao

Comments 21 pages, 8 figures, ICLR 2024

2403.00694 2024-03-04 stat.ML cs.AI cs.LG stat.ME

Defining Expertise: Applications to Treatment Effect Estimation

Alihan Hüyük, Qiyao Wei, Alicia Curth, Mihaela van der Schaar

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

2403.00329 2024-03-04 cs.AI cs.LG

Learning with Logical Constraints but without Shortcut Satisfaction

Zenan Li, Zehua Liu, Yuan Yao, Jingwei Xu, Taolue Chen, Xiaoxing Ma, Jian Lü

Comments Published as a conference paper at ICLR 2023, and code is available at https://github.com/SoftWiser-group/NeSy-without-Shortcuts