ICLR 2025 Conference Submissions

LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
Mateusz Pach, Koryna Lewandowska, Jacek Tabor, Bartosz Michał Zieliński, Dawid Damian Rymarczyk
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
CausalESC: Breaking Causal Cycles for Emotional Support Conversations with Temporal Causal HMM
Mingzheng Li, Xiao Sun, Zhuoer Zhao, Feng-Qi Cui, Jinyang Huang, Weijie Feng, Xun Yang, Zhi Liu, Meng Wang
- 20 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Unveiling Language Skills under Circuits
Hang Chen, Xinyu Yang, Zhu Jiaying, Wenya Wang
- 20 Sept 2024 (modified: 05 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
On the Entropy of Language Models in Getting Semantic from Tokens
Hang Chen, Xinyu Yang, Zhu Jiaying, Wenya Wang
- 20 Sept 2024 (modified: 18 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery
Bowei He, Lihao Yin, Huiling Zhen, Mingxuan Yuan, Chen Ma
- 20 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Actra: Optimized Transformer Architecture for Vision-Language-Action Models in Robot Learning
Yueen Ma, DaFeng Chi, Shiguang Wu, Yuecheng Liu, Yuzheng Zhuang, Jianye HAO, Irwin King
- 20 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network
Zongkai Zhang, Peng Ling, Xu Zidong, Wenming Yang, Qingmin Liao, Jing-Hao Xue
- 20 Sept 2024 (modified: 05 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
WARP: On the Benefits of Weight Averaged Rewarded Policies
Alexandre Rame, Johan Ferret, Nino Vieillard, Robert Dadashi-Tazehozi, Leonard Hussenot, Pierre-Louis Cedoz, Pier Giuseppe Sessa, Sertan Girgin, Arthur Douillard, Olivier Bachem
- 20 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Improving Diffusion-based Data Augmentation with Inversion Circle Interpolation
Yanghao Wang, Long Chen
- 20 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Segmentation using efficient residual networks with attention-fusion modules
Serdar Erisen
- 20 Sept 2024 (modified: 02 Apr 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
From Data to Model: Anomaly Detection of 3D GPR Data in CuDeRes Model Space
Xiren Zhou, Shikang Liu, Ao Chen, Xinyu Yan, Huanhuan Chen
- 20 Sept 2024 (modified: 17 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Delving into Temperature Scaling for Adaptive Conformal Prediction
HuaJun Xi, Jianguo Huang, Kangdao Liu, Lei Feng, Hongxin Wei
- 20 Sept 2024 (modified: 04 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
SimDiffPDE: Simple Diffusion Baselines for Solving Partial Differential Equations
Dongyu Luo, Jianyu Wu, Qianhong Ma, Jing Wang, Hairun Xie, Xiangyu Yue, Wanli Ouyang, Miao Zhang, SHIXIANG TANG
- 20 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
Bowei He, Lihao Yin, Huiling Zhen, Jianping Zhang, Lanqing HONG, Mingxuan Yuan, Chen Ma
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
StyleMaster: Towards Flexible Stylized Image Generation with Diffusion Models
Chengming Xu, Kai Hu, Donghao Luo, Jiangning Zhang, Qilin Wang, Xiaobin Hu, Yanwei Fu, Chengjie Wang
- 20 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Is a 3D-Tokenized LLM the Key to Reliable Autonomous Driving?
Yifan Bai, Dongming Wu, Yingfei Liu, Fan Jia, Weixin Mao, Ziheng Zhang, Yucheng Zhao, Jianbing Shen, Xing Wei, Tiancai Wang, Xiangyu Zhang
- 20 Sept 2024 (modified: 20 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Combating inherent noise for direct preference optimization
Lingfan Zhang, Chen Liu, Chengming Xu, Kai Hu, Donghao Luo, Chengjie Wang, Yuan Yao, Yanwei Fu
- 20 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Rethinking the generalization of drug target affinity prediction algorithms via similarity aware evaluation
Chenbin Zhang, Zhiqiang Hu, Jiang Chuchu, Wen Chen, JIE XU, Shaoting Zhang
- Published: 22 Jan 2025, Last Modified: 20 Feb 2025
- ICLR 2025 Oral
- Readers: Everyone
Inferring Time-Varying Internal Models of Agents Through Dynamic Structure Learning
Ashwin Moongathottathil James, Ingrid Bethus, Alexandre Muzy
- 20 Sept 2024 (modified: 05 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Enhancing Human Body Generation in Diffusion Models with Dual-Level Prior Knowledge
Chengming Xu, Wenhui Han, Xiaobin Hu, Na Zhang, Donghao Luo, Yanwei Fu, Chengjie Wang
- 20 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Learning with Analogical Reasoning for Robust Few-Shot Learning
Hailong Zhu, Jun He, Xun Yang, Xueliang Liu, Richang Hong
- 20 Sept 2024 (modified: 31 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
A Framework of SO(3)-equivariant Non-linear Representation Learning and its Application to Electronic-Structure Hamiltonian Prediction
Shi Yin, Xinyang Pan, Fengyan Wang, Lixin He
- 20 Sept 2024 (modified: 19 May 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Kolmogorov-Arnold Transformer
Xingyi Yang, Xinchao Wang
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Multi-view Object-Centric Learning with Identifiable Representations
Avinash Kori, Francesca Toni, Ben Glocker
- 20 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving
Enming Zhang, Xingyuan Dai, Yisheng Lv, Qinghai Miao
- 20 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone