ICLR 2025 Conference Submissions

Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models
Sangmin Woo, Donguk Kim, Jaehyuk Jang, Yubin Choi, Changick Kim
- 27 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Zefan Cai, Yichi Zhang, Bofei Gao, Yuliang Liu, Tianyu Liu, Keming Lu, Wayne Xiong, Yue Dong, Junjie Hu, Wen Xiao
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
Muhammad Shakeel, Yui Sudo, Yifan Peng, Chyi-Jiunn Lin, Shinji Watanabe
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Generalized Probabilistic Attention Mechanism in Transformers
DongNyeong Heo, Heeyoul Choi
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Intention Model: A Novel Explanation for In-context Learning
Yonggang Zhang, Hanzhe You, Xinmei Tian, Jie Lu
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
CryoFM: A Flow-based Foundation Model for Cryo-EM Densities
Yi Zhou, Yilai Li, Jing Yuan, Quanquan Gu
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
On the loss of context-awareness in general instruction finetuning
Yihan Wang, Andrew Bai, Nanyun Peng, Cho-Jui Hsieh
- 27 Sept 2024 (modified: 29 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
TOWARDS LAYER-WISE PERSONALIZED FEDERATED LEARNING: ADAPTIVE LAYER DISENTANGLEMENT VIA CONFLICTING GRADIENTS
Duong Minh Nguyen, Le Nam Khanh, Khoi Hoang Do, Nguyen H. Tran, Van Duc Nguyen, Zhaohui Yang, Trinh Van Chien
- 27 Sept 2024 (modified: 20 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning
Jiajun Chai, Sicheng Li, Yuqian Fu, Dongbin Zhao, Yuanheng Zhu
- Published: 22 Jan 2025, Last Modified: 12 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
TokenUnify: Scalable Autoregressive Pretraining for Large Scale EM Image Segmentation
Yinda Chen, Haoyuan Shi, Xiaoyu Liu, Te Shi, Ruobing Zhang, Dong Liu, Zhiwei Xiong, Feng Wu
- 27 Sept 2024 (modified: 24 Oct 2024)
- ICLR 2025 Conference Desk Rejected Submission
- Readers: Everyone
Mani-GS: Gaussian Splatting Manipulation with Triangular Mesh
Xiangjun Gao, Xiaoyu Li, Yiyu Zhuang, Qi Zhang, Wenbo Hu, Chaopeng Zhang, Yao Yao, Ying Shan, Long Quan
- 27 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Recycled Attention: Efficient inference for long-context language models
Fangyuan Xu, Tanya Goyal, Eunsol Choi
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
GenQA: An Instruction Dataset of LLM Generated Questions and Answers
Jiuhai Chen, Rifaa Qadri, Yuxin Wen, Neel Jain, John Kirchenbauer, Tianyi Zhou, Tom Goldstein
- 27 Sept 2024 (modified: 15 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Scaling Laws for Multilingual Language Models
Yifei He, Alon Benhaim, Barun Patra, Praneetha Vaddamanu, Sanchit Ahuja, Parul Chopra, Vishrav Chaudhary, Han Zhao, Xia Song
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Mengxuan Hu, Hongyi Wu, Zihan Guan, Ronghang Zhu, Dongliang Guo, Daiqing Qi, Sheng Li
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA
Sangmin Bae, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Seungyeon Kim, Tal Schuster
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Agile Flight with Optimization Embedded Networks
Zhichao Han, Long Xu, Liuao Pei, Fei Gao
- 27 Sept 2024 (modified: 23 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Training Task Experts through Retrieval Based Distillation
Jiaxin Ge, Xueying Jia, Vijay Viswanathan, Hongyin Luo, Graham Neubig
- 27 Sept 2024 (modified: 16 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Flexible Active Learning of PDE Trajectories
Yegon Kim, Hyunsu Kim, Juho Lee
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
QRazor: Reliable and Effortless 4-bit LLM Quantization by Significant Data Razoring
Dongyoung Lee, Seungkyu Choi, Ik Joon Chang
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data
Wenkai Li, Jiarui Liu, Andy Liu, Xuhui Zhou, Mona T. Diab, Maarten Sap
- 27 Sept 2024 (modified: 14 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
ABNet: Attention BarrierNet for Safe and Scalable Robot Learning
Wei Xiao, Tsun-Hsuan Wang, Chuang Gan, Daniela Rus
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
GENERALIZATION, ROBUSTNESS AND ADAPTABILITY OF PROGRESSIVE NEURAL COLLAPSE
Jinxin Zhou, Jiachen Jiang, Zhihui Zhu
- 27 Sept 2024 (modified: 20 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
NeuGen: Amplifying the ‘Neural’ in Neural Radiance Fields for Domain Generalization
Ahmed Rashid Qazi, Abdul Basit, Asim Iqbal
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Hot PATE: Private Aggregation of Distributions for Diverse Tasks
Edith Cohen, Benjamin Cohen-Wang, Xin Lyu, Jelani Nelson, Tamas Sarlos, Uri Stemmer
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone