ICLR 2024 Conference Submissions

RA-DIT: Retrieval-Augmented Dual Instruction Tuning
Xi Victoria Lin, Xilun Chen, Mingda Chen, Weijia Shi, Maria Lomeli, Richard James, Pedro Rodriguez, Jacob Kahn, Gergely Szilvasy, Mike Lewis, Luke Zettlemoyer, Wen-tau Yih
- Published: 16 Jan 2024, Last Modified: 15 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Differentially Private Bias-Term Fine-tuning of Foundation Models
Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Variational Language Concepts for Interpreting Pretrained Language Models
Hengyi Wang, Zhiqing Hong, Desheng Zhang, Hao Wang
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
SuperFormer: Superpixel-based Transformers for Salient Object Detection
Jinman Park, Zahra Gharaee, Paul W. Fieguth
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Improving Gradient-guided Nested Sampling for Posterior Inference
Pablo Lemos, Will Handley, Nikolay Malkin, Yoshua Bengio, Yashar Hezaveh, Laurence Perreault-Levasseur
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Structured Fine-Tuning Enables Data-Efficient Adaptation of Code Language Models
Mayank Agarwal, Yikang Shen, Bailin Wang, Yoon Kim, Jie Chen
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Guiding RL Agents with Classical Algorithms and Heuristics to Solve Combinatorial Optimization Problems on Graphs
Ali AhmadiTeshnizi, Yingxi Li, Madeleine Udell
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
Xuhui Zhou, Hao Zhu, Leena Mathur, Ruohong Zhang, Haofei Yu, Zhengyang Qi, Louis-Philippe Morency, Yonatan Bisk, Daniel Fried, Graham Neubig, Maarten Sap
- Published: 16 Jan 2024, Last Modified: 20 Mar 2024
- ICLR 2024 spotlight
- Readers: Everyone
Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Sicheng Zhu, Furong Huang, Tudor Dumitras
- Published: 16 Jan 2024, Last Modified: 21 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Self-Specialization: Uncovering Latent Expertise within Large Language Models
Junmo Kang, Hongyin Luo, Yada Zhu, James R. Glass, David Daniel Cox, Alan Ritter, Rogerio Feris, Leonid Karlinsky
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Improved Active Learning via Dependent Leverage Score Sampling
Atsushi Shimizu, Xiaoou Cheng, Christopher Musco, Jonathan Weare
- Published: 16 Jan 2024, Last Modified: 10 Apr 2024
- ICLR 2024 oral
- Readers: Everyone
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Visual Data-Type Understanding does not emerge from scaling Vision-Language Models
Vishaal Udandarao, Max F Burg, Samuel Albanie, Matthias Bethge
- Published: 16 Jan 2024, Last Modified: 10 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Revisiting differentially private XGBoost: are random decision trees really better than greedy ones?
Erchi Wang, Arinbjörn Kolbeinsson, Luca Foschini, Yu-Xiang Wang
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
Suyu Ge, Yunan Zhang, Liyuan Liu, Minjia Zhang, Jiawei Han, Jianfeng Gao
- Published: 16 Jan 2024, Last Modified: 16 Mar 2024
- ICLR 2024 oral
- Readers: Everyone
Memory Efficient Neural Processes via Constant Memory Attention Block
Leo Feng, Frederick Tung, Hossein Hajimirsadeghi, Yoshua Bengio, Mohamed Osama Ahmed
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
FAIR-Ensemble: Homogeneous Deep Ensembling Naturally Attenuates Disparate Group Performances
Wei-Yin Ko, Daniel D'souza, Karina Nguyen, Randall Balestriero, Sara Hooker
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
GEOFFair: a GEOmetric Framework for Fairness
Alessandro Maggio, Luca Giuliani, Roberta Calegari, Michele Lombardi, Michela Milano
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
EFFICIENT QUANTUM STATE RECONSTRUCTION USING UNSUPERVISED LEARNING FOR QUANTUM CIRCUIT CUTTING
vinitha balachandran, Benjamin Chen Ming Choong, Nitin Shivaraman, Zhehui Wang, Liwei Yang, Rick Siow Mong Goh, Tao Luo
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
DIVERSITY OF THOUGHT IMPROVES REASONING ABILITIES OF LARGE LANGUAGE MODELS
Ranjita Naik, Varun Chandrasekaran, Mert Yuksekgonul, Hamid Palangi, Besmira Nushi
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding
Eslam Mohamed BAKR, Mohamed Ayman Mohamed, Mahmoud Ahmed, Habib Slim, Mohamed Elhoseiny
- Published: 16 Jan 2024, Last Modified: 16 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Re-evaluating Retrosynthesis Algorithms with Syntheseus
Krzysztof Maziarz, Austin Tripp, Guoqing Liu, Megan Stanley, Shufang Xie, Piotr Gaiński, Philipp Seidl, Marwin Segler
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
An Efficient Tester-Learner for Halfspaces
Aravind Gollakota, Adam Klivans, Konstantinos Stavropoulos, Arsen Vasilyan
- Published: 16 Jan 2024, Last Modified: 12 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces
Tales Henrique Carvalho, Kenneth Tjhia, Levi Lelis
- Published: 16 Jan 2024, Last Modified: 14 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-Temporal Reasoning
Mohamed Aghzal, Erion Plaku, Ziyu Yao
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone