ICLR 2024 Conference Submissions

BOtied: Multi-objective Bayesian optimization with tied multivariate ranks
Ji Won Park, Natasa Tagasovska, Michael Maser, Stephen Ra, Kyunghyun Cho
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Privately Aligning Language Models with Reinforcement Learning
Fan Wu, Huseyin A Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan Kulkarni, Robert Sim
- Published: 16 Jan 2024, Last Modified: 05 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
YaRN: Efficient Context Window Extension of Large Language Models
Bowen Peng, Jeffrey Quesnelle, Honglu Fan, Enrico Shippole
- Published: 16 Jan 2024, Last Modified: 09 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Evaluating and Improving Generation Consistency of Large Language Models via A Divide-Conquer-Reasoning Approach
Wendi Cui, Jiaxin Zhang, Zhuohang Li, Damien Lopez, Kamalika Das, Bradley Malin, Sricharan Kumar
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
On the Generalization of Training-based ChatGPT Detection Methods
Han Xu, Jie Ren, Pengfei He, Shenglai Zeng, Yingqian Cui, Amy Liu, Hui Liu, Jiliang Tang
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Divergence at the Interpolation Threshold: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
Rylan Schaeffer, Zachary Robertson, Akhilan Boopathy, Mikail Khona, Ila R Fiete, Andrey Gromov, Sanmi Koyejo
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics
Jenny Hamer, Eleni Triantafillou, Bart van Merriënboer, Stefan Kahl, Holger Klinck, tom denton, Vincent Dumoulin
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
What Improves the Generalization of Graph Transformer? A Theoretical Dive into Self-attention and Positional Encoding
Hongkang Li, Meng Wang, Tengfei Ma, Sijia Liu, ZAIXI ZHANG, Pin-Yu Chen
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
UGSL: A Unified Framework for Benchmarking Graph Structure Learning
Bahare Fatemi, Sami Abu-El-Haija, Anton Tsitsulin, Mehran Kazemi, Dustin Zelle, Neslihan Bulut, Jonathan Halcrow, Bryan Perozzi
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Estimating Performative Effects in Dynamical Systems: the advantage of sequential observations
Gary Cheng, Moritz Hardt, Celestine Mendler-Dünner
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Accelerating Sinkhorn algorithm with sparse Newton iterations
Xun Tang, Michael Shavlovsky, Holakou Rahmanian, Elisa Tardini, Kiran Koshy Thekumparampil, Tesi Xiao, Lexing Ying
- Published: 16 Jan 2024, Last Modified: 05 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
$\sigma$-PCA: a unified neural model for linear and nonlinear principal component analysis
Fahdi Kanavati, Lucy Katsnith, Masayuki Tsuneki
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity
Lu Yin, Shiwei Liu, AJAY KUMAR JAISWAL, Souvik Kundu, Zhangyang Wang
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
UGC: UNIVERSAL GRAPH COARSENING
Mohit Kataria, Sandeep Kumar, Jayadeva Jayadeva
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
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
- Published: 16 Jan 2024, Last Modified: 05 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Stream: A Generalized Continual Learning Benchmark and Baseline
Iordanis Fostiropoulos, Jiaye Zhu, Laurent Itti
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination
Lu Wen, Songan Zhang, Eric H. Tseng, Huei Peng
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Word Importance Explains How Prompts Affect Language Model Outputs
Stefan Hackmann, Haniyeh Mahmoudian, Mark Steadman, Michael Schmidt
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales
Aaron Chan, Zhiyuan Zeng, Wyatt Lake, Brihi Joshi, Hanjie Chen, Xiang Ren
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Pre-training with Random Orthogonal Projection Image Modeling
Maryam Haghighat, Peyman Moghadam, Shaheer Mohamed, Piotr Koniusz
- Published: 16 Jan 2024, Last Modified: 13 Apr 2024
- ICLR 2024 spotlight
- Readers: Everyone
Correct-by-design Safety Critics using Non-contractive Binary Bellman Operators
Agustin Castellano, Hancheng Min, Juan Andres Bazerque, Enrique Mallada
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Hypergraph Neural Networks through the Lens of Message Passing: A Common Perspective to Homophily and Architecture Design
Lev Telyatnikov, Maria Sofia Bucarelli, Guillermo Bernardez, Olga Zaghen, Simone Scardapane, Pietro Lio
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
FeatUp: A Model-Agnostic Framework for Features at Any Resolution
Stephanie Fu, Mark Hamilton, Laura E. Brandt, Axel Feldmann, Zhoutong Zhang, William T. Freeman
- Published: 16 Jan 2024, Last Modified: 15 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Diversity-aware Continual Learning with Latent Knowledge Hypergraph
Jiayi Chen, Kishlay Jha, Aidong Zhang
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Mechanistic Neural Networks
Adeel Pervez, Francesco Locatello, Efstratios Gavves
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone