ICLR 2025 Conference Submissions

TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types
Jiankang Chen, Tianke Zhang, Changyi Liu, Haojie Ding, Yaya Shi, cheng.feng, Huihui Xiao, Bin Wen, Fan Yang, Tingting Gao, Di ZHANG
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Structure-Preserving Operator Learning
Nacime Bouziani, Nicolas Boulle
- 23 Sept 2024 (modified: 10 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing
Cai Yuchen, Ding Cao, Xinyuan Liu, Guiquan Liu
- 23 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition
Hongyu Qu, Hailiang Gao, Rui Yan, Wenguan Wang, Xiangbo Shu
- 23 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Crafting Zero-Cost Proxy Metrics for Neural Architecture Search via Symbolic Regression
Quan Minh Phan, Ngoc Hoang Luong
- 23 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Masked Image Modeling Representations
Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter, Johannes Brandstetter
- Published: 22 Jan 2025, Last Modified: 21 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Exploiting Hidden Symmetry to Improve Objective Perturbation for DP Linear Learners with a Nonsmooth L1-Norm
Du Chen, Geoffrey A. Chua
- Published: 22 Jan 2025, Last Modified: 09 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
ESE: Espresso Sentence Embeddings
Xianming LI, Zongxi Li, Jing Li, Haoran Xie, Qing Li
- Published: 22 Jan 2025, Last Modified: 25 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Vision-LSTM: xLSTM as Generic Vision Backbone
Benedikt Alkin, Maximilian Beck, Korbinian Pöppel, Sepp Hochreiter, Johannes Brandstetter
- Published: 22 Jan 2025, Last Modified: 11 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
On the Fourier analysis in the SO(3) space : the EquiLoPO Network
Dmitrii Zhemchuzhnikov, Sergei Grudinin
- Published: 22 Jan 2025, Last Modified: 19 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
Xin Zhang, Jiawei Du, Ping Liu, Joey Tianyi Zhou
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Generating Synthetic Genotypes using Diffusion Models
Philip Kenneweg, Raghuram Dandinasivara Rangaram, Xiao Luo, Barbara Hammer, Alexander Schoenhuth
- 23 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging
Tianhui Song, Weixin Feng, Shuai Wang, Xubin Li, Tiezheng Ge, Bo Zheng, Limin Wang
- 23 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation
Dekai Zhu, Yan Di, Stefan Gavranovic, Slobodan Ilic
- 23 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Test-time Alignment of Diffusion Models without Reward Over-optimization
Sunwoo Kim, Minkyu Kim, Dongmin Park
- Published: 22 Jan 2025, Last Modified: 29 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Seeing the part and knowing the whole: Object-Centric Learning with Inter-Feature Prediction
Junhong Zou, Xiangyu Zhu, Zhen Lei
- 23 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series Modeling
Yicheng Luo, Bowen Zhang, Zhen Liu, Qianli Ma
- 23 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Robust Conformal Prediction with a Single Binary Certificate
Soroush H. Zargarbashi, Aleksandar Bojchevski
- Published: 22 Jan 2025, Last Modified: 07 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
Senthooran Rajamanoharan, Tom Lieberum, Nicolas Sonnerat, Arthur Conmy, Vikrant Varma, Janos Kramar, Neel Nanda
- 23 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Selective Induction Heads: How Transformers Select Causal Structures in Context
Francesco D'Angelo, Francesco Croce, Nicolas Flammarion
- Published: 22 Jan 2025, Last Modified: 17 May 2025
- ICLR 2025 Poster
- Readers: Everyone
NeuralPlane: Structured 3D Reconstruction in Planar Primitives with Neural Fields
Hanqiao Ye, Yuzhou Liu, Yangdong Liu, Shuhan Shen
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Oral
- Readers: Everyone
PEARL: Parallel Speculative Decoding with Adaptive Draft Length
Tianyu Liu, Yun Li, Qitan Lv, Kai Liu, Jianchen Zhu, Winston Hu, Xiao Sun
- Published: 22 Jan 2025, Last Modified: 10 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Diffusion-based Extreme Image Compression with Compressed Feature Initialization
Zhiyuan Li, Yanhui Zhou, Hao Wei, Chenyang Ge, Ajmal Saeed Mian
- 23 Sept 2024 (modified: 25 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Deep Learning-based Heuristic Construction for Routing Problems with Dynamic Encoder and Dual-Channel Decoder Architecture
Jianlin Chen, Jianping Luo
- 23 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
BCE vs. CE in Deep Feature Learning
Qiufu Li, Huibin Xiao, Linlin Shen
- 23 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone