ICLR 2025 Conference Submissions

JoPA: Explaining Large Language Model's Generation via Joint Prompt Attribution
Yurui Chang, Bochuan Cao, Yujia Wang, Jinghui Chen, Lu Lin
- 26 Sept 2024 (modified: 16 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments
Anindya Sarkar, Srikumar Sastry, Aleksis Pirinen, Nathan Jacobs, Yevgeniy Vorobeychik
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DC3DO: Diffusion Classifier for 3D Objects
Nursena Koprucu, Meher Shashwat Nigam, Shicheng Luke Xu, Biruk Abere Ambaw, Andrew Rodriguez, Gabriele Dominici, Sharvaree Vadgama, Berfin Inal, Alberto Tono
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Learning mirror maps in policy mirror descent
Carlo Alfano, Sebastian Rene Towers, Silvia Sapora, Chris Lu, Patrick Rebeschini
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World
Joshua Kazdan, Rylan Schaeffer, Apratim Dey, Matthias Gerstgrasser, Rafael Rafailov, David L. Donoho, Sanmi Koyejo
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Certified Defense on the Fairness of Graph Neural Networks
Yushun Dong, Binchi Zhang, Hanghang Tong, Jundong Li
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Dual-Stream Adapters for Anomaly Segmentation
Shyam Nandan Rai, Massimiliano Mancini, Marco Ciccone, Iuliana Georgescu, Zeynep Akata, Barbara Caputo, Carlo Masone
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Understanding Optimization in Deep Learning with Central Flows
Jeremy Cohen, Alex Damian, Ameet Talwalkar, J Zico Kolter, Jason D. Lee
- Published: 22 Jan 2025, Last Modified: 02 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
MazeNet: An Accurate, Fast, & Scalable Deep Learning Solution for Steiner Minimum Trees
Gabriel Diaz, Toros Arikan, Richard Baraniuk
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures
Dang Nguyen, Wenhan Yang, Rathul Anand, Yu Yang, Baharan Mirzasoleiman
- Published: 22 Jan 2025, Last Modified: 31 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
MalTrans: Unsupervised Binary Code Translation with Application to Malware Detection
Minghao Hu, Junzhe Wang, Weisen Zhao, Lannan Luo
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
Rylan Schaeffer, Hailey Schoelkopf, Brando Miranda, Gabriel Mukobi, Varun Madan, Adam Ibrahim, Herbie Bradley, Stella Biderman, Sanmi Koyejo
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SafeText: Safe Text-to-image Models via Aligning the Text Encoder
Yuepeng Hu, Zhengyuan Jiang, Neil Zhenqiang Gong
- 26 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Spherical Tree-Sliced Wasserstein Distance
Hoang V. Tran, Thanh Chu, Minh-Khoi Nguyen-Nhat, Huyen Trang Pham, Tam Le, Tan Minh Nguyen
- Published: 22 Jan 2025, Last Modified: 18 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Repetition Improves Language Model Embeddings
Jacob Mitchell Springer, Suhas Kotha, Daniel Fried, Graham Neubig, Aditi Raghunathan
- Published: 22 Jan 2025, Last Modified: 10 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking
Danqing Wang, Jianxin Ma, Fei Fang, Lei Li
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Investigating Online RL in World Models
Uljad Berdica, Kelvin Li, Michael Beukman, Alexander David Goldie, Mattie Fellows, Perla Maiolino, Jakob Nicolaus Foerster
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Bayesian Experimental Design Via Contrastive Diffusions
Jacopo Iollo, Christophe Heinkelé, Pierre Alliez, Florence Forbes
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Yuuki Yamanaka, Tomoya Yamashita
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
EndoAssistant: A Large-scale Vision-Language Dataset for Endoscopic Surgery Understanding from Open-Source Videos
Xuan Gong, Balu Harshavardan Koduru, Yuanhao Zhai, Shun Liu, Nan Xi, Xi Tang, Yuan Zhang, Tenzin Lhakpa, Yunjie Tian, Yuxuan Sun, Tianyu Luan, Ziqing Xue, Junsong Yuan, David Doermann
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
MorphoDiff: Cellular Morphology Painting with Diffusion Models
Zeinab Navidi, Jun Ma, Esteban Miglietta, Le Liu, Anne E Carpenter, Beth A Cimini, Benjamin Haibe-Kains, BO WANG
- Published: 22 Jan 2025, Last Modified: 06 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Understanding the Training and Generalization of Pretrained Transformer for Sequential Decision Making
Hanzhao Wang, Yu Pan, Fupeng Sun, Shang Liu, KALYAN TEJA TALLURI, Guanting Chen, Xiaocheng Li
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Evaluating Large Language Models' Capability to Conduct Cyberattacks On Embedded Devices
Fred Heiding, Simon Lermen
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Paint by Inpaint: Learning to Add Image Objects by Removing Them First
navve wasserman, Noam Rotstein, Roy Ganz, Ron Kimmel
- 26 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences
Soroush Mehraban, Mohammad Javad Rajabi, Babak Taati
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone