ICLR 2025 Conference Submissions

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss
Zesen Cheng, Hang Zhang, Kehan Li, Sicong Leng, Zhiqiang Hu, Fei Wu, Deli Zhao, Xin Li, Lidong Bing
- 14 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism
Dengchun Li, Naizheng Wang, Zihao Zhang, Haoyang Yin, Lei Duan, Meng Xiao, Yuanchun Zhou, Mingjie Tang
- 14 Sept 2024 (modified: 15 Oct 2024)
- ICLR 2025 Conference Desk Rejected Submission
- Readers: Everyone
SUN: Training-free Machine Unlearning via Subspace
Chengyao Qian, Jing Wu, Trung Le, Dinh Phung, Mehrtash Harandi
- 14 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Size-aware Compression of 3D Gaussians with Fine-grained Mixed Precision Quantization
Shuzhao Xie, Jiahang Liu, Weixiang Zhang, Shijia Ge, Sicheng Pan, Chen Tang, Yunpeng Bai, Zhi Wang
- 14 Sept 2024 (modified: 12 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning
Yuncong Yang, Han Yang, Jiachen Zhou, Peihao Chen, Hongxin Zhang, Yilun Du, Chuang Gan
- 14 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Estimating Statistical Similarity Between Product Distributions
Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel, Dimitrios Myrisiotis, A. Pavan, N. V. Vinodchandran
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Robust Multi-modal Learning with Shifted Feature Reweighting Against Spurious Correlations
Chenyu You, Weicheng Dai, Yifei Min, Tiansheng Wen, Lawrence Hamilton Staib, James s Duncan
- 14 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Simple yet Effective Incomplete Multi-view Clustering: Similarity-level Imputation and Intra-view Hybrid-group Prototype Construction
Shengju Yu, Zhibin Dong, Siwei Wang, Pei Zhang, Yi Zhang, Xinwang Liu, Naiyang Guan, Tiejun Li, Yiu-ming Cheung
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Balancing Interpretability and Accuracy: Energy-Ensemble Concept Bottleneck Models for Enhanced Concept Inference
Dasom Ahn, Sangwon Kim, HyeongJin Kim, In-su Jang, Kwang-Ju Kim, Byoung Chul Ko
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Weak-to-Strong Enhanced Vision Model
Jianyuan Guo, Hanting Chen, Chengcheng Wang, Kai Han, Chang Xu, Yunhe Wang
- 14 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Empirical Study on Enhancing Efficiency in Masked Image Modeling Pre-training
Jianyuan Guo, Zhiwei Hao, Kai Han, Yehui Tang, Han Wu, Xinghao Chen, Han Hu, Chang Xu, Yunhe Wang
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
Xiangyu Zeng, Kunchang Li, Chenting Wang, Xinhao Li, Tianxiang Jiang, Ziang Yan, Songze Li, Yansong Shi, Zhengrong Yue, Yi Wang, Yali Wang, Yu Qiao, Limin Wang
- Published: 22 Jan 2025, Last Modified: 04 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
Mingkun Zhang, Keping Bi, Wei Chen, Jiafeng Guo, Xueqi Cheng
- Published: 22 Jan 2025, Last Modified: 14 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Maintaining Adversarial Robustness in Continuous Learning
Xiaolei Ru, Gang Yan, Xiaowei Cao, Wenjia Wei, Xia Zhu, Jack Murdoch Moore, Xin-Ya Zhang
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
Junlin Han, Jianyuan Wang, Andrea Vedaldi, Philip Torr, Filippos Kokkinos
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Simplified Mamba with Disentangled Dependency Encoding for Long-Term Time Series Forecasting
Zixuan Weng, Jindong Han, Wenzhao Jiang, Hao Liu
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Prompt-Aware Adapter: Towards Learning Adaptive Visual Tokens for Multimodal Large Language Models
Yue Zhang, Hehe Fan, Wei Ji, Yongkang Wong, Roger Zimmermann, Yi Yang
- 14 Sept 2024 (modified: 04 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
ProtoLLM: Training and Example-free LLMs for Few-shot Tabular Learning
Peng Wang, Dongsheng Wang, He Zhao, Hangting Ye, Dan dan Guo
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
IFAdapter: Instance feature control for grounded Text-to-Image Generation
Yinwei Wu, Xianpan Zhou, bing ma, Xuefeng Su, Kai Ma, Xinchao Wang
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Reward-Robust RLHF in LLMs
Yuzi Yan, Xingzhou Lou, Jialian Li, YipinZhang, Jian Xie, Chao Yu, Yu Wang, Dong Yan, Yuan Shen
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Solving Video Inverse Problems Using Image Diffusion Models
Taesung Kwon, Jong Chul Ye
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
How Far Is Video Generation from World Model: A Physical Law Perspective
Bingyi Kang, Yang Yue, Rui Lu, Zhijie Lin, Yang Zhao, Kaixin Wang, Gao Huang, Jiashi Feng
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Detecting Problematic Questions to Support Math Word Problem Design
Mao-Siang Chen, Yu-Hang Deng, An-Zi Yen
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Preserving Large Activations: The Key to KV Cache Pruning
Rui Kong, Yuanchun Li, qingtian feng, Linghe Kong, Yunxin Liu
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Jailbreaking as a Reward Misspecification Problem
Zhihui Xie, Jiahui Gao, Lei Li, Zhenguo Li, Qi Liu, Lingpeng Kong
- Published: 22 Jan 2025, Last Modified: 21 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone