ICLR 2025 Conference Submissions

Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking
Mattia Segu, Luigi Piccinelli, Siyuan Li, Yung-Hsu Yang, Luc Van Gool, Bernt Schiele
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding
Xiner Li, Yulai Zhao, Chenyu Wang, Gabriele Scalia, Gökcen Eraslan, Surag Nair, Tommaso Biancalani, Shuiwang Ji, Aviv Regev, Sergey Levine, Masatoshi Uehara
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
TabDPT: Scaling Tabular Foundation Models
Junwei Ma, Valentin Thomas, Rasa Hosseinzadeh, Hamidreza Kamkari, Alex Labach, Jesse C. Cresswell, Keyvan Golestan, Guangwei Yu, Maksims Volkovs, Anthony L. Caterini
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Model-Free Offline Reinforcement Learning with Enhanced Robustness
Chi Zhang, Zain Ulabedeen Farhat, George K. Atia, Yue Wang
- Published: 22 Jan 2025, Last Modified: 14 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Unleashing the Potential of Classification with Semantic Similarity for Deep Imbalanced Regression
Ruizhi Pu
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Alternating Projections With Volume Sampling
Alireza Entezari, Arunava Banerjee, Leila Kalantari
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Virtual Community: A Generative Social World for Embodied AI
Qinhong Zhou, Hongxin Zhang, Yutian Chen, Zheyuan Zhang, Xiangye Lin, Jincheng Yang, Lixing Fang, Jiageng Liu, Xinyu Sun, Chuang Gan
- 19 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
ACID: A Comprehensive Dataset for AI-Created Image Detection
Haoming Lu, Kai Wang, Bin Sun, Hovhannes Margaryan, Xingqian Xu, Humphrey Shi
- 19 Sept 2024 (modified: 12 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want
Weifeng Lin, Xinyu Wei, Ruichuan An, Peng Gao, Bocheng Zou, Yulin Luo, Siyuan Huang, Shanghang Zhang, Hongsheng Li
- Published: 22 Jan 2025, Last Modified: 22 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
E-DETR: Evidential Deep Learning for End-to-End Uncertainty Estimation in Object Detection
Tejas Pandey, Nick Pears, William A P Smith, John Alexander McDermid
- 19 Sept 2024 (modified: 31 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Programming Refusal with Conditional Activation Steering
Bruce W. Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy, Erik Miehling, Pierre Dognin, Manish Nagireddy, Amit Dhurandhar
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Intrinsic Behavioral Variability Facilitates Flexible Representations: A Neuromotor Developmental Perspective
Jonathan S. Daniels, Jordan Taylor, Shawn Lawrence Beaulieu
- 19 Sept 2024 (modified: 26 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
Min Shi, Fuxiao Liu, Shihao Wang, Shijia Liao, Subhashree Radhakrishnan, Yilin Zhao, De-An Huang, Hongxu Yin, Karan Sapra, Yaser Yacoob, Humphrey Shi, Bryan Catanzaro, Andrew Tao, Jan Kautz, Zhiding Yu, Guilin Liu
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Finetuning Weather Foundation Models to Develop Climate Model Parameterizations
Aman Gupta, Sujit Roy, Johannes Schmude, Vishal Gaur, Wei Ji Leong, Manil Maskey, Rahul Ramachandran, Aditi Sheshadri
- 19 Sept 2024 (modified: 22 Feb 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Let Your Features Tell The Differences: Understanding Graph Convolution By Feature Splitting
Yilun Zheng, Xiang Li, Sitao Luan, Xiaojiang Peng, Lihui Chen
- Published: 22 Jan 2025, Last Modified: 26 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels
Zhizheng Liu, Joe Lin, Wayne Wu, Bolei Zhou
- Published: 22 Jan 2025, Last Modified: 04 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Marginalization Consistent Mixture of Separable Flows for Probabilistic Irregular Time Series Forecasting
Vijaya Krishna Yalavarthi, Randolf Scholz, Christian Klötergens, Kiran Madhusudhanan, Stefan Born, Lars Schmidt-Thieme
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
MMFNet: Multi-Scale Frequency Masking Neural Network for Multivariate Time Series Forecasting
Aitian Ma, Mo Sha, Dongsheng Luo
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Long-form Hallucination Detection with Self-elicitation
Zihang Liu, Jiawei Guo, Xinxin Lu, Hao Zhang, Jiajun Bu, Haishuai Wang
- 19 Sept 2024 (modified: 05 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities
Lili Zhang, Min Wu, Tomas E. Ward
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Identifying treatment response subgroups in observational time-to-event data
Vincent Jeanselme, Chang Ho Yoon, Fabian Falck, Brian Tom, Jessica Barrett
- 19 Sept 2024 (modified: 29 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with $0.1k$ Parameters
Aitian Ma, Mo Sha, Dongsheng Luo
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SSLA: A Generalized Attribution Method for Interpreting Self-Supervised Learning without Downstream Task Dependency
Zhiyu Zhu, Jiayu Zhang, NAN YANG, Xinyi Zhang, Zhibo Jin, Jianlong Zhou, Fang Chen
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
$\alpha$-Divergence Loss Function for Neural Density Ratio Estimation
Yoshiaki Kitazawa
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Dynamic Cross-Layer Prefix Alignment for Resolving Label Preference Discrepancies in LLMs Fine-Tuning
Jiayu Zhang, Liwei Hou, Yinan Peng, Canran Xiao, Weihao Luo
- 19 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone