ICLR 2025 Conference Submissions

FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing
Zekai Li, Jintu Zheng, Ji Liu, Han Liu, Haowei Zhu, Zeping Li, Fuwei Yang, Haiduo Huang, Jinzhang Peng, Dong Li, Lu Tian, Emad Barsoum
- 14 Sept 2024 (modified: 16 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Denoising with a Joint-Embedding Predictive Architecture
Dengsheng Chen, Jie Hu, Xiaoming Wei, Enhua Wu
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Hyper-Connections
Defa Zhu, Hongzhi Huang, Zihao Huang, Yutao Zeng, Yunyao Mao, Banggu Wu, Qiyang Min, Xun Zhou
- Published: 22 Jan 2025, Last Modified: 05 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
Tiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, Ling Liu
- Published: 22 Jan 2025, Last Modified: 10 Apr 2025
- ICLR 2025 Oral
- Readers: Everyone
Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark
Bing Cao, Quanhao Lu, Jiekang Feng, Qilong Wang, Pengfei Zhu, Qinghua Hu
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecasting
FENG SHIBO, Wanjin Feng, Xingyu Gao, Peilin Zhao, Zhiqi Shen
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time
Yi Ding, Bolian Li, Ruqi Zhang
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate
Jiahe Du, Kaixiong Zhou, Xinyu Hong, Zhaozhuo Xu, Jinbo Xu, Xiao Huang
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
KEEP: Towards a Knowledge-Enhanced Explainable Prompting Framework for Vision-Language Models
Yequan Bie, Luyang Luo, Andong Tan, Zhixuan CHEN, Hao Chen
- 14 Sept 2024 (modified: 22 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Temporal Distribution-aware Quantization for Diffusion Models
Ruiyi Zhan, Jiaxin Chen, Hongyu Yang, Di Huang, Yunhong Wang
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding
Kaiyan Zhang, Jianyu Wang, Ning Ding, Biqing Qi, Ermo Hua, Xingtai Lv, Bowen Zhou
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Ranking-aware adapter for text-driven image ordering with CLIP
Wei-Hsiang Yu, Yen-Yu Lin, Ming-Hsuan Yang, Yi-Hsuan Tsai
- Published: 22 Jan 2025, Last Modified: 17 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion
Kaizhe Hu, Zihang Rui, Yao He, Yuyao Liu, Pu Hua, Huazhe Xu
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Test-time Correction with Human Feedback: An Online 3D Detection System via Visual Prompting
Zetong Yang, Hanxue Zhang, Yanan SUN, Li Chen, Fei Xia, Fatma Guney, Hongyang Li
- 14 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation
Qingwen Bu, Hongyang Li, Li Chen, Jisong Cai, Jia Zeng, Heming Cui, Maoqing Yao, Yu Qiao
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
AutoGenDA: Automated Generative Data Augmentation for Imbalanced Classifications
Tsz-Him Cheung, Dit-Yan Yeung
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
BroadWay: Boost Your Text-to-Video Generation Model in a Training-free Way
Jiazi Bu, Pengyang Ling, Pan Zhang, Tong Wu, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Dahua Lin, Jiaqi Wang
- 14 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Deciphering and Enhancing Commonsense Reasoning in LLMs from the Perspective of Intrinsic Factual Knowledge Retrieval
Yiqun Wang, Sile Hu, Chaoqun Wan, Yonggang Zhang, Xiang Tian, Yaowu Chen, Xu Shen, Jieping Ye
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Evaluating Diversity of LLM-generated Datasets: A Classification Perspective
Yuchang Zhu, Huizhe Zhang, Bingzhe Wu, Jintang Li, Zibin Zheng, Peilin Zhao, Liang Chen, Yatao Bian
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
BiC-Occ: Bi-directional Circulated 3D Occupancy Prediction for Autonomous Driving
Zhiwen Yang, Yuxin Peng
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
Long Xing, Qidong Huang, Xiaoyi Dong, Jiajie Lu, Pan Zhang, Yuhang Zang, Yuhang Cao, Conghui He, Jiaqi Wang, Feng Wu, Dahua Lin
- 14 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
ReMatching Dynamic Reconstruction Flow
Sara Oblak, Despoina Paschalidou, Sanja Fidler, Matan Atzmon
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
KnowTrace: Explicit Knowledge Tracing for Structured Retrieval-Augmented Generation
Rui Li, Quanyu Dai, Zeyu Zhang, Xu Chen, Zhenhua Dong, Ji-Rong Wen
- 14 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Balancing Differential Discriminative Knowledge For Clothing-Irrelevant Lifelong Person Re-identification
Zhenyu Cui, Jiahuan Zhou, Yuxin Peng
- 14 Sept 2024 (modified: 12 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Adaptive Proximal Gradient Optimizer: Addressing Gradient Inexactness in Predict+Optimize Framework
Shunyu Wu, Jingcheng Wang, Huihuang Cai, Xinwei Xiao
- 14 Sept 2024 (modified: 06 May 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone