ICLR 2025 Conference Submissions

K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language Models
Jaehyung Seo, Heuiseok Lim
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Shell Games: Control Protocols for Adversarial AI Agents
Aryan Bhatt, Cody Rushing, Adam Kaufman, Vasil Georgiev, Tyler Tracy, Akbir Khan, Buck Shlegeris
- 28 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Charting the Design Space of Neural Graph Representations for Subgraph Matching
Vaibhav Raj, Indradyumna Roy, Ashwin Ramachandran, Soumen Chakrabarti, Abir De
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification
Hyunji Jung, Hanseul Cho, Chulhee Yun
- Published: 22 Jan 2025, Last Modified: 26 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Contextual Kernels for Task-Aware Fine-Tuning in Vision-Language Models
Shilin Zhang, YAN MING
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
ZEPHYR GAN: REDEFINING GAN WITH FLEXIBLE GRADIENT CONTROL
Anuradha Kumari, Ritik Mishra, M. Tanveer
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates
Kaiyuan Gao, Yusong Wang, Haoxiang Guan, Zun Wang, Qizhi Pei, John E. Hopcroft, Kun He, Lijun Wu
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
ProcBench: Benchmark for Multi-Step Reasoning and Following Procedure
Ippei Fujisawa, Sensho Nobe, Hiroki Seto, Rina Onda, Yoshiaki Uchida, Hiroki IKOMA, Pei-Chun Chien, Ryota Kanai
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Exploiting the Kurtosis Concentration Property for Image quality improvement
Aniket Roy, Maitreya Suin, Anshul Shah, Ketul Shah, Jiang Liu, Rama Chellappa
- 28 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Faster Language Models with Better Multi-Token Prediction Using Tensor Decomposition
Artem Basharin, Andrei Chertkov, Ivan Oseledets
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
The Unreasonable Ineffectiveness of the Deeper Layers
Andrey Gromov, Kushal Tirumala, Hassan Shapourian, Paolo Glorioso, Dan Roberts
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark
Federico Berto, Chuanbo Hua, Junyoung Park, Laurin Luttmann, Yining Ma, Fanchen Bu, Jiarui Wang, Haoran Ye, Minsu Kim, Sanghyeok Choi, Nayeli Gast Zepeda, André Hottung, Jianan Zhou, Jieyi Bi, Yu Hu, Fei Liu, Hyeonah Kim, Jiwoo Son, Haeyeon Kim, Davide Angioni et al. (13 additional authors not shown)
- 28 Sept 2024 (modified: 09 Nov 2024)
- ICLR 2025 Conference Desk Rejected Submission
- Readers: Everyone
FedGO : Federated Ensemble Distillation with GAN-based Optimality
Won-Jun Jang, Hyeon-Seo Park, Si-Hyeon Lee
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Reinforcement Learning and Heuristics for Hardware-Efficient Constrained Code Design
Sunil Sudhakaran, Mert Pilanci, Mark Horowitz
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Towards Understanding Memory buffer based Continual Learning
Guodong Zheng, Peng Wang, Li Shen
- 28 Sept 2024 (modified: 23 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Wyckoff Transformer: Generation of Symmetric Crystals
Nikita Kazeev, Ruiming Zhu, Ignat Romanov, Wei Nong, Andrey E Ustyuzhanin, Shuya Yamazaki, Kedar Hippalgaonkar
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
AuPair: Golden Example Pairs for Code Repair
Aditi Mavalankar, Hassan Mansoor, Zita Marinho, Mariia Samsikova, Tom Schaul
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Attack on LLMs: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
Hongyi Liu, Shaochen Zhong, Xintong Sun, Minghao Tian, Zirui Liu, Ruixiang Tang, Jiayi Yuan, Yu-Neng Chuang, Li Li, Soo-Hyun Choi, Rui Chen, Vipin Chaudhary, Xia Hu
- 28 Sept 2024 (modified: 04 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Grey-box Prompt Optimization and Fine-Tuning for Cloud-Edge LLM Agents
Ya Liu, Kai Yang, Yu Zhu, Keying Yang, Chengtao Jian, Wuguang Ni, Xiaozhou Ye, Ye Ouyang
- 28 Sept 2024 (modified: 29 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Convergence Of Consistency Model With Multistep Sampling Under General Data Assumptions
Yiding Chen, Yiyi Zhang, Owen Oertell, Wen Sun
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Debiased Medical Report Generation with High-Frequency Amplification
Changhun Lee, Jiwon Kim, Chiehyeon Lim
- 28 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
FreeFlow: Latent Flow Matching for Free Energy Difference Estimation
Ege Erdogan, Radoslav Ralev, Mika Rebensburg, Céline Marquet, Leon Klein, Hannes Stark
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
OpenPL: Realistic Evaluation of Prompt Learning for VLM in Open Environments
Zi-Kang Wang, Song-Lin Lv, Hao-Zhe Tan, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
TopoLM: brain-like spatio-functional organization in a topographic language model
Neil Rathi, Johannes Mehrer, Badr AlKhamissi, Taha Osama A Binhuraib, Nicholas Blauch, Martin Schrimpf
- Published: 22 Jan 2025, Last Modified: 11 May 2025
- ICLR 2025 Oral
- Readers: Everyone
Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates
Cristian Meo, Ksenia Sycheva, Carlo Saccardi, Anirudh Goyal, Pietro Lio, Justin Dauwels
- 28 Sept 2024 (modified: 11 Nov 2024)
- ICLR 2025 Conference Desk Rejected Submission
- Readers: Everyone