ICLR 2025 Conference Submissions

Watermarking using Semantic-aware Speculative Sampling: from Theory to Practice
Baihe Huang, Hanlin Zhu, Julien Piet, Banghua Zhu, Jason D. Lee, Kannan Ramchandran, Michael Jordan, Jiantao Jiao
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Generative Parameter Efficient Fine-Tuning
Chinmay Savadikar, Xi Song, Tianfu Wu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Scalable Diffusion for Bio-topological Representation Learning on Brain Graphs
Mujie Liu, Chenze Wang, Qichao Dong, Jing Ren, Jingjing Zhou, Vidya Saikrishna, Feng Xia
- 26 Sept 2024 (modified: 16 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
BAT-CLIP: Bimodal Test-Time Adaptation for CLIP
Sarthak Kumar Maharana, Baoming Zhang, Leonid Karlinsky, Rogerio Feris, Yunhui Guo
- 26 Sept 2024 (modified: 12 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Arctic-SnowCoder: Demystifying High-Quality Data in Code Pretraining
Yuxiang Wei, Hojae Han, Rajhans Samdani
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
Ziyang Wu, Tianjiao Ding, Yifu Lu, Druv Pai, Jingyuan Zhang, Weida Wang, Yaodong Yu, Yi Ma, Benjamin David Haeffele
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Learning Disentangled Representations for Fairness with Limited Demographics
Shenyu Lu, Xiaoqian Wang
- 26 Sept 2024 (modified: 22 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Level-Set Parameters: Novel Data for 3D Shape Analysis
Huan Lei, Hongdong Li, Andreas Geiger, Anthony Dick
- 26 Sept 2024 (modified: 28 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Law of the Weakest Link: Cross Capabilities of Large Language Models
Ming Zhong, Aston Zhang, Xuewei Wang, Rui Hou, Wenhan Xiong, Chenguang Zhu, Zhengxing Chen, Liang Tan, Chloe Bi, Mike Lewis, Sravya Popuri, Sharan Narang, Melanie Kambadur, Dhruv Mahajan, Sergey Edunov, Jiawei Han, Laurens van der Maaten
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks
Xingxuan Li, Weiwen Xu, Ruochen Zhao, Fangkai Jiao, Shafiq Joty, Lidong Bing
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1
Karthik Valmeekam, Kaya Stechly, Atharva Gundawar, Subbarao Kambhampati
- 26 Sept 2024 (modified: 03 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Rehearsal-Free Continual Federated Learning with Synergistic Regularization
Yichen Li, Yuying Wang, Tianzhe Xiao, Haozhao Wang, Yining Qi, Ruixuan Li
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
BenTo: Benchmark Reduction with In-Context Transferability
Hongyu Zhao, Ming Li, Lichao Sun, Tianyi Zhou
- Published: 22 Jan 2025, Last Modified: 07 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
The Complexity Dynamics of Grokking
Branton DeMoss, Silvia Sapora, Jakob Nicolaus Foerster, Nick Hawes, Ingmar Posner
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Differentially Private Learned Indexes
Jianzhang Du, Tilak Mudgal, Rutvi Rahul Gadre, Yukui Luo, Chenghong Wang
- 26 Sept 2024 (modified: 15 Oct 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
Shuoyuan Wang, Yixuan Li, Hongxin Wei
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Forward Learning with Differential Privacy
Mingqian Feng, Zeliang Zhang, Jinyang Jiang, Yijie Peng, Chenliang Xu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Adversarial Masked Autoencoder Purifier with Defense Transferability
Yuan-Chih Chen, Chun-Shien Lu
- 26 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models
Abhishek Dutta, Yen-Che Hsiao
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
MatMamba: A Matryoshka State Space Model
Abhinav Shukla, Sai Vemprala, Aditya Kusupati, Ashish Kapoor
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Efficient Gun Detection in Real-World Videos: Challenges and Solutions
Badhan Chandra Das, Yanzhao Wu, M. Hadi Amini
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Leveraging System-Prompt Attention to Counteract Novel Jailbreak Attacks
Charlotte Siska, Anush Sankaran
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Towards Making Linear Attention Usable
Armin Gerami, Monte Hoover, Ramani Duraiswami
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Round and Round We Go! What makes Rotary Positional Encodings useful?
Federico Barbero, Alex Vitvitskyi, Christos Perivolaropoulos, Razvan Pascanu, Petar Veličković
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
On the self-verification limitations of large language models on reasoning and planning tasks
Kaya Stechly, Karthik Valmeekam, Subbarao Kambhampati
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone