ICLR 2025 Conference Submissions

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution
Yun Zhang, Wei Li, Simiao Li, Hanting Chen, Zhijun Tu, Bingyi Jing, Shaohui Lin, Jie Hu, Wenjia Wang
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Model
Hieu Trung Nguyen, YIWEN CHEN, Vikram Voleti, Varun Jampani, Huaizu Jiang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Multi-Perspective Test-Time Prompt Tuning for Global, Local Visuals, and Language
Zhaohong Huang, Yuxin Zhang, JingJing Xie, Fei Chao, Rongrong Ji
- 26 Sept 2024 (modified: 21 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
qNBO: quasi-Newton Meets Bilevel Optimization
Sheng Fang, Yongjin Liu, Wei Yao, Chengming Yu, Jin Zhang
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
FACTOR: Factoring Complexity and Context Length in Long-Context Model Evaluation
Hongyi Liu, Zhuoming Chen, Yang Zhou, Beidi Chen
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games
Yanzheng Chen, Jun Yu
- Published: 22 Jan 2025, Last Modified: 28 Mar 2025
- ICLR 2025 Oral
- Readers: Everyone
Toward Escaping Model Collapse: Aligning Generated Images as a New Modality
Shentong Mo, Sukmin Yun
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding
Zhenyu Yang, Yuhang Hu, Zemin Du, Dizhan Xue, Shengsheng Qian, Jiahong Wu, Fan Yang, Weiming Dong, Changsheng Xu
- Published: 22 Jan 2025, Last Modified: 16 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Disentangled and Self-Explainable Node Representation Learning
Simone Piaggesi, André Panisson, Megha Khosla
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Deconstructing Denoising Diffusion Models for Self-Supervised Learning
Xinlei Chen, Zhuang Liu, Saining Xie, Kaiming He
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation
Abdullah Enes Doruk, Erhan Oztop, Hasan Fehmi Ates
- 26 Sept 2024 (modified: 17 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing
Yifei Yang, zouying cao, Qiguang Chen, Libo Qin, Dongjie Yang, Zhi Chen, hai zhao
- 26 Sept 2024 (modified: 16 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Efficient Multi-Level Learning for Dense Object Detection
ZhaoHui Zheng, Yuming Chen, Ping Wang, Le Zhang, Xiang Li, Qibin Hou, Ming-Ming Cheng
- 26 Sept 2024 (modified: 19 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Map to Optimal: Adapting Graph Out-of-Distribution in Test Time
Haoxiang Zhang, Zhuofeng Li, Qiannan Zhang, Ziyi Kou, Lianyong Qi, Juncheng Li, Shichao Pei
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Evaluating topological fitness of human brain-inspired sub-circuits in Echo State Networks
Bach Viet Nguyen, Tianlong Chen, Shu Yang, Bojian Hou, Li Shen, Duy Duong-Tran
- 26 Sept 2024 (modified: 30 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Hindsight Planner: A Closed-loop few-shot planner for Embodied Instruction Following
yuxiao Yang, Shenao Zhang, Zhihan Liu, Huaxiu Yao, Zhaoran Wang
- 26 Sept 2024 (modified: 14 Oct 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution
Simiao Li, Yun Zhang, Wei Li, Hanting Chen, Wenjia Wang, Bingyi Jing, Shaohui Lin, Jie Hu
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
SONNET: Solar-disaggregation-based Day-ahead Probabilistic Net Load Forecasting with Transformers
Kang Pu, Yuqi Nie, Mian Jia, Yue Zhao, Nam H Nguyen, H. Vincent Poor
- 26 Sept 2024 (modified: 24 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Auditing Predictive Models for Intersectional Biases
Kate Boxer, Edward McFowland III, Daniel B. Neill
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models
Shang Wang
- Published: 22 Jan 2025, Last Modified: 26 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting
Huanyu Zhang, Chang Xu, YiFan Zhang, Zhang Zhang, Liang Wang, Tieniu Tan, Jiang Bian
- 26 Sept 2024 (modified: 13 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance
Dominik Fuchsgruber, Tim Postuvan, Stephan Günnemann, Simon Geisler
- Published: 22 Jan 2025, Last Modified: 06 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
U3D: Unlocking the Video Prior for High Fidelity Sparse Novel View Synthesis and 3D Generation
Fan Yang, Jianfeng Zhang, Chaoyue Song, Zhongcong Xu, Xiu Li, Guan Luo, Zhongang Cai, Jiashi Feng, Guosheng Lin
- 26 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Learnability of Discrete Dynamical Systems under High Classification Noise
Zirou Qiu, Zakaria Mehrab, Abhijin Adiga, Madhav Marathe, S. S. Ravi, Daniel Rosenkrantz, Richard Stearns, Anil Kumar Vullikanti
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Navigating the Labyrinth: Evaluating and Enhancing LLMs’ Ability to Reason About Search Problems
Nasim Borazjanizadeh, Roei Herzig, Trevor Darrell, Rogerio Feris, Leonid Karlinsky
- 26 Sept 2024 (modified: 15 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone