ICLR 2025 Conference Submissions

ReHub: Linear Complexity Graph Transformers with Adaptive Hub-Spoke Reassignment
Tomer Borreda, Daniel Freedman, Or Litany
- 16 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Federated Adapter on Foundation Models: An Out-Of-Distribution Approach
yiyuan yang, Guodong Long, Tianyi Zhou, Qinghua Lu, Shanshan Ye, Jing Jiang
- 16 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Instance-aware Generalized Multi-task Visual Grounding
Ming Dai, Lingfeng Yang, Wenxuan Cheng, Jiedong Zhuang, Zhenhua Feng, Wankou Yang
- 16 Sept 2024 (modified: 26 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
DPD-LoRA: Dynamic Prompt-Driven Low-Rank Adaptation for Improved Generalization
Chushan Zhang, Ruihan Lu, Zeeshan Hayder, Hongdong Li
- 16 Sept 2024 (modified: 22 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Self-Supervised Feature Re-Representation via Lennard-Jones Potential Loss
Jianlong Kwan, Jiayu Xiong, Dilong Li, Jing Wang
- 16 Sept 2024 (modified: 19 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling
Zeyue Tian, Zhaoyang Liu, Ruibin Yuan, Jiahao Pan, Qifeng Liu, Xu Tan, Qifeng Chen, Wei Xue, Yike Guo
- 16 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
SynFER: Towards Boosting Facial Expression Recognition with Synthesis Data
Xilin He, Cheng Luo, Xiaole Xian, Bing Li, Siyang Song, Muhammad Haris Khan, Weicheng Xie, Zongyuan Ge, Linlin Shen
- 16 Sept 2024 (modified: 30 Oct 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
Sicong Leng, Yun Xing, Zesen Cheng, Yang Zhou, Hang Zhang, Xin Li, Deli Zhao, Shijian Lu, Chunyan Miao, Lidong Bing
- 16 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment
Yizhi Song, Liu He, Zhifei Zhang, Soo Ye Kim, He Zhang, Wei Xiong, Zhe Lin, Brian L. Price, Scott Cohen, Jianming Zhang, Daniel Aliaga
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling
Zhengqiang ZHANG, Ruihuang Li, Lei Zhang
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code
Zimu Lu, Aojun Zhou, Ke Wang, Houxing Ren, Weikang Shi, Junting Pan, Mingjie Zhan, Hongsheng Li
- Published: 22 Jan 2025, Last Modified: 17 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Data Extrapolation for Text-to-image Generation on Small Datasets
Senmao Ye
- 16 Sept 2024 (modified: 20 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering
Jingqiu Zhou, Lue Fan, Zhaoxiang Zhang, Hongsheng Li
- 16 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
SwitchLoss: A Novel Optimization Scheme for Imbalanced Regression
Jovana Aleksic, Miguel García-Remesal
- 16 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Fast Tensor-Based Multi-View Clustering with Anchor Probability Transition Matrix
Wei Feng, Dongyuan Wei, Qianqian Wang
- 16 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Consistency Calibration: Improving Uncertainty Calibration via Consistency among Perturbed Neighbors
Linwei Tao, Haolan Guo, Minjing Dong, Chang Xu
- 16 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Point-Calibrated Spectral Neural Operators
Xihang Yue, Linchao Zhu, Yi Yang
- 16 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
VideoAlchemy: Open-set Personalization in Video Generation
Tsai-Shien Chen, Aliaksandr Siarohin, Willi Menapace, Yuwei Fang, Ivan Skorokhodov, Jun-Yan Zhu, Kfir Aberman, Ming-Hsuan Yang, Sergey Tulyakov
- 16 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Transformers Learn Low Sensitivity Functions: Investigations and Implications
Bhavya Vasudeva, Deqing Fu, Tianyi Zhou, Elliott Kau, Youqi Huang, Vatsal Sharan
- Published: 22 Jan 2025, Last Modified: 16 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
TLDR: Token-Level Detective Reward Model for Large Vision Language Models
Deqing Fu, Tong Xiao, Rui Wang, Wang Zhu, Pengchuan Zhang, Guan Pang, Robin Jia, Lawrence Chen
- Published: 22 Jan 2025, Last Modified: 24 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
Xunhao Lai, Jianqiao Lu, Yao Luo, Yiyuan Ma, Xun Zhou
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Oral
- Readers: Everyone
Training-Free Activation Sparsity in Large Language Models
James Liu, Pragaash Ponnusamy, Tianle Cai, Han Guo, Yoon Kim, Ben Athiwaratkun
- Published: 22 Jan 2025, Last Modified: 25 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Beautifying Diffusion Models: Learning Context-Aware Filters for Robust Dense Prediction on Test-Time Corrupted Images
Gabriel Tjio, Nhat Chung, Yun Xing, Xiaofeng Cao, Ivor Tsang, Chee Kwoh, Qing Guo
- 16 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
PRIME: Protect Your Videos From Malicious Editing
Guanlin Li, Shuai Yang, Jie Zhang, Han Qiu, Tianwei Zhang
- 16 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Statistical Advantages of Perturbing Cosine Router in Mixture of Experts
Huy Nguyen, Pedram Akbarian, Huyen Trang Pham, Thien Trang Nguyen Vu, Shujian Zhang, Nhat Ho
- Published: 22 Jan 2025, Last Modified: 02 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone