ICLR 2025 Conference Submissions

MMEval: Evaluating Video Generation Models for Motion Quality
Prateksha Udhayanan, Kuldeep Kulkarni, Balaji Vasan Srinivasan
- 26 Sept 2024 (modified: 26 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Towards Aligned Data Forgetting via Twin Machine Unlearning
haoxuan ji, Yuyao Sun, Zhenxing Niu, Gang Hua, Rong Jin, Quan Wang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
Jun Zhang, Jue WANG, Huan Li, Lidan Shou, Ke Chen, Yang You, Guiming Xie, Xuejian Gong, Kunlong Zhou
- Published: 22 Jan 2025, Last Modified: 30 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Revisit, Extend, and Enhance Hessian-Free Influence Functions
Ziao Yang, Han Yue, Jian Chen, Hongfu Liu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
MME-FINANCE: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning
Ziliang Gan, Yu Lu, Dong Zhang, Haohan Li, Che Liu, Jian Liu, Ji Liu, Haipang WU, Chaoyou Fu, Zenglin Xu, Rongjunchen Zhang, Yong Dai
- 26 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
Erik Jones, Arjun Patrawala, Jacob Steinhardt
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Quantifying Emergence in Neural Networks: Insights from Pruning and Training Dynamics
Faisal Saleh Alshinaifi, Zeyad Almoaigel, Johnny Jingze Li, Abdulla Kuleib, Gabriel A. Silva
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
RDHNet: Addressing Rotational and Permutational Symmetries in Continuous Multi-Agent Systems
Dongzi Wang, Lilan Huang, Muning Wen, Xiao Teng, TENG LI, Minglong Li
- 26 Sept 2024 (modified: 18 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
GeNIe: Generative Hard Negative Images Through Diffusion
Soroush Abbasi Koohpayegani, Anuj Singh, Navaneet K L, Hamed Pirsiavash, Hadi Jamali-Rad
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
UniCoTT: A Unified Framework for Structural Chain-of-Thought Distillation
Xianwei Zhuang, Zhihong Zhu, Zhichang Wang, Xuxin Cheng, Yuexian Zou
- Published: 22 Jan 2025, Last Modified: 04 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Towards Stable Learning in Predictive Coding Networks
Myoung Hoon Ha, Yoondo Sung, Youngha Jo, Hyunjun Kim, Sang Wan Lee
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Neural Fluid Simulation on Geometric Surfaces
Haoxiang Wang, Tao Yu, Hui Qiao, Qionghai Dai
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
RandLoRA: Full rank parameter-efficient fine-tuning of large models
Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Cristian Rodriguez-Opazo, Anton van den Hengel, Ehsan Abbasnejad
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks
Chen Xiong, Xiangyu Qi, Pin-Yu Chen, Tsung-Yi Ho
- 26 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Data Interpreter: An LLM Agent For Data Science
Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Chenxing Wei, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Xiangru Tang, Xiangtao Lu et al. (7 additional authors not shown)
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning
Nilay Yilmaz, Maitreya Patel, Yiran Lawrence Luo, Tejas Gokhale, Chitta Baral, Suren Jayasuriya, Yezhou Yang
- Published: 22 Jan 2025, Last Modified: 04 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Learning local equivariant representations for quantum operators
Zhanghao Zhouyin, Zixi Gan, Shishir Kumar Pandey, Linfeng Zhang, Qiangqiang Gu
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Continual Task Learning through Adaptive Policy Self-Composition
Shengchao Hu, Yuhang Zhou, Ziqing Fan, Jifeng Hu, Li Shen, Ya Zhang, Dacheng Tao
- 26 Sept 2024 (modified: 20 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Hiding Images in Diffusion Models by Editing Learned Score Functions
Haoyu Chen, Yunqiao Yang, Nan Zhong, Kede Ma
- 26 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments
Ke Yi, Yuhui Xu, Heng Chang, Chen Tang, Yuan Meng, Tong Zhang, Jia Li
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Out-of-Distribution Detection in Class Incremental Learning
Wenjun Miao, Guansong Pang, Trong-Tung Nguyen, Ruohuan Fang, Jin Zheng, Xiao Bai
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations
Hongyu Ke, Jack Morris, Kentaro Oguchi, Xiaofei Cao, Yongkang Liu, Haoxin Wang, Yi Ding
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
On the Inflation of KNN-Shapley Value
Ziao Yang, Han Yue, Jian Chen, Hongfu Liu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization
Hanyang Zhao, Genta Indra Winata, Anirban Das, Shi-Xiong Zhang, David Yao, Wenpin Tang, Sambit Sahu
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Binary Hypothesis Testing for Softmax Models and Leverage Score Models
Yeqi Gao, Yuzhou Gu, Zhao Song, Junze Yin
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone