ICLR 2024 Conference Submissions

Personalization Mitigates the Perils of Local SGD for Heterogeneous Distributed Learning
Kumar Kshitij Patel, Nidham Gazagnadou, Lingxiao Wang, Lingjuan Lyu
- 19 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Less is More: Fewer Interpretable Region via Submodular Subset Selection
Ruoyu Chen, Hua Zhang, Siyuan Liang, Jingzhi Li, Xiaochun Cao
- Published: 16 Jan 2024, Last Modified: 05 Mar 2024
- ICLR 2024 oral
- Readers: Everyone
Cameras as Rays: Pose Estimation via Ray Diffusion
Jason Y. Zhang, Amy Lin, Moneish Kumar, Tzu-Hsuan Yang, Deva Ramanan, Shubham Tulsiani
- Published: 16 Jan 2024, Last Modified: 21 Apr 2024
- ICLR 2024 oral
- Readers: Everyone
ResTran: A GNN Alternative To Learn Graph With Features
Shota Saito, Takanori Maehara, Mark Herbster
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences
Grigory Malinovsky, Eduard Gorbunov, Peter Richtárik, Samuel Horváth
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Domain constraints improve risk prediction when outcome data is missing
Sidhika Balachandar, Nikhil Garg, Emma Pierson
- Published: 16 Jan 2024, Last Modified: 15 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Learning Multi-Agent Communication with Contrastive Learning
Yat Long Lo, Biswa Sengupta, Jakob Nicolaus Foerster, Michael Noukhovitch
- Published: 16 Jan 2024, Last Modified: 13 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Improving Domain Generalization with Domain Relations
Huaxiu Yao, Xinyu Yang, Xinyi Pan, Shengchao Liu, Pang Wei Koh, Chelsea Finn
- Published: 16 Jan 2024, Last Modified: 21 Apr 2024
- ICLR 2024 spotlight
- Readers: Everyone
Critique Ability of Large Language Models
Liangchen Luo, Zi Lin, Yinxiao Liu, Lei Shu, Yun Zhu, Jingbo Shang, Lei Meng
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Causal Representation Learning and Inference for Generalizable Cross-Domain Predictions
Naiyu Yin, Hanjing Wang, Amit Dhurandhar, Tian Gao, Qiang Ji
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
VTruST : Controllable value function based subset selection for Data-Centric Trustworthy AI
Soumi Das, Shubhadip Nag, Shreyyash Sharma, Suparna Bhattacharya, Sourangshu Bhattacharya
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.
Raj Ghugare, Matthieu Geist, Glen Berseth, Benjamin Eysenbach
- Published: 16 Jan 2024, Last Modified: 05 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Overcoming Generic Knowledge Loss with Selective Parameter Update
Wenxuan Zhang, Paul Janson, Rahaf Aljundi, Mohamed Elhoseiny
- 19 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning
Shangmin Guo, Yi Ren, Stefano V Albrecht, Kenny Smith
- Published: 16 Jan 2024, Last Modified: 21 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
Wenxuan Zhang, Youssef Mohamed, Bernard Ghanem, Philip Torr, Adel Bibi, Mohamed Elhoseiny
- Published: 16 Jan 2024, Last Modified: 28 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Sporadicity in Decentralized Federated Learning: Theory and Algorithm
Shahryar Zehtabi, Rohit Parasnis, Seyyedali Hosseinalipour, Christopher Brinton
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
LMDX: Language Model-based Document Information Extraction and Localization
Vincent Perot, Kai Kang, Florian Luisier, Guolong Su, Xiaoyu Sun, Ramya Sree Boppana, Zilong Wang, Jiaqi Mu, Hao Zhang, Nan Hua
- 19 Sept 2023 (modified: 15 Feb 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Compound Returns Reduce Variance in Reinforcement Learning
Brett Daley, Martha White, Marlos C. Machado
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation
Yipin Guo, Zihao Li, Qinyuan Ren
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
REX: Rapid Exploration and eXploitation for AI agents
Rithesh R N, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Le Xue, Weiran Yao, Yihao Feng, Zeyuan Chen, Akash Gokul, Devansh Arpit, Ran Xu, Phil L Mui, Huan Wang, Caiming Xiong, Silvio Savarese
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Generating Images with 3D Annotations Using Diffusion Models
Wufei Ma, Qihao Liu, Jiahao Wang, Angtian Wang, Xiaoding Yuan, Yi Zhang, Zihao Xiao, Guofeng Zhang, Beijia Lu, Ruxiao Duan, Yongrui Qi, Adam Kortylewski, Yaoyao Liu, Alan Yuille
- Published: 16 Jan 2024, Last Modified: 21 Apr 2024
- ICLR 2024 spotlight
- Readers: Everyone
Momentum Particle Maximum Likelihood
Jen Ning Lim, Juan Kuntz, Samuel Power, Adam Michael Johansen
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Grounding Everything: Emerging Localization Properties in Vision-Language Transformers
Walid Bousselham, Felix Petersen, Vittorio Ferrari, Hilde Kuehne
- 19 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
PatchCraft: Learning Optimized Image Patch for Enhanced Visual Attention of CLIP
Razieh Rezaei, Masoud Jalili Sabet, Ashkan Khakzar, Daniel Rueckert, Philip Torr, Jindong Gu
- 19 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Brain encoding models based on binding multiple modalities across audio, language, and vision
Khushbu Pahwa, SUBBA REDDY OOTA, Advaith Malladi, Maneesh Kumar Singh, Manish Gupta, Bapi Raju Surampudi
- 19 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone