ICLR 2025 Conference Submissions

Differential Transformer
Tianzhu Ye, Li Dong, Yuqing Xia, Yutao Sun, Yi Zhu, Gao Huang, Furu Wei
- Published: 22 Jan 2025, Last Modified: 10 Mar 2025
- ICLR 2025 Oral
- Readers: Everyone
Style-Coherent Multi-Modality Image Fusion
Xinran Qin, Yuning Cui, Shangquan Sun, Wenqi Ren, Xiaochun Cao
- 22 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
ControlSpeech: Towards Simultaneous Zero-shot Speaker Cloning and Zero-shot Language Style Control
Shengpeng Ji, Jialong Zuo, Wen Wang, Minghui Fang, Qian Chen, Ziyue Jiang, Hai Huang, Zehan Wang, Xize Cheng, Siqi Zheng, Zhou Zhao
- 22 Sept 2024 (modified: 13 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Not Every Image is Worth a Thousand Words: Quantifying Originality in Stable Diffusion
Adi Haviv, Shahar Sarfaty, Uri Y. Hacohen, Niva Elkin-Koren, Roi Livni, Amit Haim Bermano
- 22 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
DIESEL - Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs
Ben Ganon, Alon Zolfi, Omer Hofman, Inderjeet Singh, Hisashi Kojima, Yuval Elovici, Asaf Shabtai
- 22 Sept 2024 (modified: 04 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
HYBRID MODEL COLLABORATION FOR SIGN LANGUAGE TRANSLATION WITH VQ-VAE AND RAG ENHANCED LLMS
Jian Ma, Wenguan Wang, Yi Yang, Weili Guan, Feng Zheng
- 22 Sept 2024 (modified: 23 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks
Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh, Rasool Jalili
- 22 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Balanced conic rectified flow
Kim Shin Seong, Mingi Kwon, Jaeseok Jeong, Youngjung Uh
- 22 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Distilling Non-Autoregressive Model Knowledge for Autoregressive De Novo Peptide Sequencing
Xiang Zhang, Jiaqi Wei, Zijie Qiu, Sheng Xu, Zhi Jin, ZhiQiang Gao, Nanqing Dong, Siqi Sun
- 22 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Instance-level Consistent Graph With Unsupervised Human Parts for Person Re-identification
Jinsheng Xiao, Jingyi Wu, Shurui Wang, Honggang Xie, Hailong Shi, Xingyu Gao
- 22 Sept 2024 (modified: 24 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Decoupling Backdoors from Main Task: Toward the Effective and Durable Backdoors in Federated Learning
Zhaoxin Wang, Handing Wang, Cong Tian, Yaochu Jin
- 22 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Structuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing Models
Hanmo Liu, Shimin Di, Jialiang Wang, Zhili Wang, Jiachuan Wang, Xiaofang Zhou, Lei Chen
- Published: 22 Jan 2025, Last Modified: 20 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion
Dexuan Ding, Lei Wang, Liyun Zhu, Tom Gedeon, Piotr Koniusz
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Video Instruction Tuning with Synthetic Data
Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li, Zejun MA, Ziwei Liu, Chunyuan Li
- 22 Sept 2024 (modified: 19 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank
Feiyu Zhu, Yuming Zhang, Changpeng Cai, Chenghao He, Xiuyuan Guo, Jiao Li, Peizhe Wang, Junhao Su, Jialin Gao
- 22 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
On the Relation Between Linear Diffusion and Power Iteration
Dana Weitzner, Mauricio Delbracio, Peyman Milanfar, Raja Giryes
- 22 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Enhancing Multilingual Reasoning in LLMs: Insights from Cross-Linguistic Correlations and Optimal Data Proportions
Jiangkuo Wang, Suyv Ma, Mingpeng Wei
- Published: 22 Jan 2025, Last Modified: 08 Apr 2025
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Personalized Federated Learning via Variational Massage Passing
Chenxi Zhong, Hang Liu, Xiaojun Yuan
- 22 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Towards Realistic Long-tailed Semi-supervised Learning in an Open World
Yuanpeng He, Lijian Li, Xiancai Chen, Chi-Man Pun, Wenpin Jiao, Zhi Jin
- 22 Sept 2024 (modified: 12 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Semi-Supervised Underwater Object Detection with Image Enhancement Guided by Attribute-based Data Distribution
Wenzhang Zhou, caixia xia, Baojie Fan, Leo Shawn, Xiangzhu Meng, Jiandong Tian
- 22 Sept 2024 (modified: 26 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Make It Count: Text-to-Image Generation with an Accurate Number of Objects
Lital Binyamin, Yoad Tewel, Hilit Segev, Eran Hirsch, Royi Rassin, Gal Chechik
- 22 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Model Cautiousness: Towards Safer Deployment in Critical Domains
Gianluca Detommaso
- 22 Sept 2024 (modified: 12 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner Framework
Junliang Chen, Huaiyuan Xu, Yi Wang, Lap-Pui Chau
- Published: 22 Jan 2025, Last Modified: 21 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
HSR-Enhanced Sparse Attention Acceleration
Bo Chen, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song
- 22 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation
Yongxian Wei, Zixuan Hu, Li Shen, Zhenyi Wang, Chun Yuan, Dacheng Tao
- Published: 22 Jan 2025, Last Modified: 15 May 2025
- ICLR 2025 Oral
- Readers: Everyone