ICLR 2025 Conference Submissions

CycleResearcher: Improving Automated Research via Automated Review
Yixuan Weng, Minjun Zhu, Guangsheng Bao, Hongbo Zhang, Jindong Wang, Yue Zhang, Linyi Yang
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?
Che Liu, Zhongwei Wan, Haozhe Wang, Yinda Chen, Talha Qaiser, Chen Jin, Fariba Yousefi, Nikolay Burlutskiy, Rossella Arcucci
- 13 Sept 2024 (modified: 29 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
Guoxuan Xia, Olivier Laurent, Gianni Franchi, Christos-Savvas Bouganis
- Published: 22 Jan 2025, Last Modified: 20 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Adapting Monte Carlo Tree Search for Generative Flow Network Training
Adamo Young, Kanika Madan, Amir Khasahmadi
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Towards Improving Exploration through Sibling Augmented GFlowNets
Kanika Madan, Alex Lamb, Emmanuel Bengio, Glen Berseth, Yoshua Bengio
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs
Che Liu, Cheng Ouyang, Zhongwei Wan, Haozhe Wang, Wenjia Bai, Rossella Arcucci
- 13 Sept 2024 (modified: 29 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Wavelet Latent Diffusion (WaLa): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings
Aditya Sanghi, Aliasghar Khani, Pradyumna Reddy, Arianna Rampini, Derek Cheung, Kamal Rahimi Malekshan, Kanika Madan, Hooman Shayani
- 13 Sept 2024 (modified: 06 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
Xingrui Wang, Wufei Ma, Angtian Wang, Shuo Chen, Adam Kortylewski, Alan Yuille
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models
Xin Xu, Jiaxin ZHANG, Tianhao Chen, Zitong Chao, Jishan Hu, Can Yang
- Published: 22 Jan 2025, Last Modified: 25 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Can LLMs Solve Longer Math Word Problems Better?
Xin Xu, Tong Xiao, Zitong Chao, Zhenya Huang, Can Yang, Yang Wang
- Published: 22 Jan 2025, Last Modified: 15 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation
Abhishek Aich, Yumin Suh, Samuel Schulter, Manmohan Chandraker
- Published: 22 Jan 2025, Last Modified: 29 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
HFT: Half Fine-Tuning for Large Language Models
Tingfeng Hui, Zhenyu Zhang, Shuohuan Wang, Weiran Xu, Yu Sun, Hua Wu
- 13 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
Muyang Li, Yujun Lin, Zhekai Zhang, Tianle Cai, Xiuyu Li, Junxian Guo, Enze Xie, Chenlin Meng, Jun-Yan Zhu, Song Han
- Published: 22 Jan 2025, Last Modified: 12 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models
Muhammad Jehanzeb Mirza, Mengjie Zhao, Zhuoyuan Mao, Sivan Doveh, Wei Lin, Paul Gavrikov, Michael Dorkenwald, Shiqi Yang, Saurav Jha, Hiromi Wakaki, Yuki Mitsufuji, Horst Possegger, Rogerio Feris, Leonid Karlinsky, James R. Glass
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
OCN: Learning Object-centric Representations for Unsupervised Multi-object Segmentation
Yafei YANG, Zihui Zhang, Bo Yang
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream
Jia Li, Jiaxu Wang, Junhao He, Mingyuan Sun, Renjing Xu, Qiang Zhang, Jiahang Cao, Ziyi Zhang, Yi Gu, Jingkai SUN
- 13 Sept 2024 (modified: 28 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Riemannian Transformation Layers for General Geometries
Ziheng Chen, Yue Song, Xiaojun Wu, Nicu Sebe
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Archilles' Heel in Semi-open LLMs: Hiding Bottom against Recovery Attacks
Hanbo Huang, Yihan Li, Bowen Jiang, Ruoyu Sun, Lin Liu, Zhuotao Liu, Bo Jiang, Shiyu Liang
- 13 Sept 2024 (modified: 16 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry
Ziheng Chen, Yue Song, Xiaojun Wu, Gaowen Liu, Nicu Sebe
- Published: 22 Jan 2025, Last Modified: 16 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Frequency-Decoupled Cross-Modal Knowledge Distillation
Junhong Liu, Yuan Zhang, Tao Huang, Haozhao Wang, Wenchao Xu, Shanghang Zhang, Renyu Yang
- 13 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Addressing Inverse Problems in Frame Restoration with Siamese Conditional Variational Autoencoders
Yongchen Zhou, Richard Jiang, Qiang Ni
- 13 Sept 2024 (modified: 21 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
KARA: Enhancing High-Dimensional Data Processing with Learnable Activations
Yongchen Zhou, Richard Jiang, Qiang Ni
- 13 Sept 2024 (modified: 21 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Gyrogroup Batch Normalization
Ziheng Chen, Yue Song, Xiaojun Wu, Nicu Sebe
- Published: 22 Jan 2025, Last Modified: 16 May 2025
- ICLR 2025 Poster
- Readers: Everyone
HENP: Dynamic Pruning via Neuron Entropy
Boyuan Wang, Richard Jiang
- 13 Sept 2024 (modified: 23 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data
Hugo Thimonier, José Lucas De Melo Costa, Fabrice Popineau, Arpad Rimmel, Bich-Liên DOAN
- Published: 22 Jan 2025, Last Modified: 12 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone