ICLR

MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents

Yanqi Dai, Huanran Hu, Lei Wang, Shengjie Jin, Xu Chen, Zhiwu Lu

Comments Accepted for the 13th International Conference on Learning Representations (ICLR 2025)

Bridging Compressed Image Latents and Multimodal Large Language Models

Chia-Hao Kao, Cheng Chien, Yu-Jen Tseng, Yi-Hsin Chen, Alessandro Gnutti, Shao-Yuan Lo, Wen-Hsiao Peng, Riccardo Leonardi

Comments Accepted by ICLR 2025

Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling

Wei Guo, Molei Tao, Yongxin Chen

Comments ICLR 2025 camera ready https://openreview.net/forum?id=P6IVIoGRRg

CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models

Zheng Chong, Xiao Dong, Haoxiang Li, Shiyue Zhang, Wenqing Zhang, Xujie Zhang, Hanqing Zhao, Dongmei Jiang, Xiaodan Liang

Comments Accepted by ICLR 2025

Attention as a Hypernetwork

Simon Schug, Seijin Kobayashi, Yassir Akram, João Sacramento, Razvan Pascanu

Comments ICLR 2025 (Oral); Code available at https://github.com/smonsays/hypernetwork-attention

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling

Cristian Rodriguez-Opazo, Ehsan Abbasnejad, Damien Teney, Hamed Damirchi, Edison Marrese-Taylor, Anton van den Hengel

Comments ICLR 2025. arXiv admin note: text overlap with arXiv:2312.14400

Looking Backward: Streaming Video-to-Video Translation with Feature Banks

Feng Liang, Akio Kodaira, Chenfeng Xu, Masayoshi Tomizuka, Kurt Keutzer, Diana Marculescu

Comments ICLR 2025. Project page: https://jeff-liangf.github.io/projects/streamv2v

Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards

Xiaoyu Yang, Jie Lu, En Yu

Comments ICLR 2025 Poster

Efficient Off-Policy Learning for High-Dimensional Action Spaces

Fabian Otto, Philipp Becker, Ngo Anh Vien, Gerhard Neumann

Comments Accepted at ICLR 2025

Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation

Zhao Song, Mingquan Ye, Junze Yin, Lichen Zhang

Comments ICLR 2025

Human alignment of neural network representations

Lukas Muttenthaler, Jonas Dippel, Lorenz Linhardt, Robert A. Vandermeulen, Simon Kornblith

Comments Accepted for publication at ICLR 2023

Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model

Jiarui Jin, Haoyu Wang, Hongyan Li, Jun Li, Jiahui Pan, Shenda Hong

Comments 21 pages, 8 figures, accepted by International Conference on Learning Representations 2025

Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy

Mingyang Zhao, Gaofeng Meng, Dong-Ming Yan

Comments [ICLR 2025] Project and code at: https://github.com/zikai1/OAReg

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression

Megh Shukla, Aziz Shameem, Mathieu Salzmann, Alexandre Alahi

Comments ICLR 2025

Injecting Universal Jailbreak Backdoors into LLMs in Minutes

Zhuowei Chen, Qiannan Zhang, Shichao Pei

Comments Accepted to ICLR 2025

On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth

Gennadiy Averkov, Christopher Hojny, Maximilian Merkert

Comments ICLR 2025 conference paper

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities

Peng Xu, Wei Ping, Xianchao Wu, Chejian Xu, Zihan Liu, Mohammad Shoeybi, Bryan Catanzaro

Comments Accepted at ICLR 2025

GraphArena: Evaluating and Exploring Large Language Models on Graph Computation

Jianheng Tang, Qifan Zhang, Yuhan Li, Nuo Chen, Jia Li

Comments ICLR 2025 camera ready version

NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative

Asmar Nadeem, Faegheh Sardari, Robert Dawes, Syed Sameed Husain, Adrian Hilton, Armin Mustafa

Comments International Conference on Learning Representations (ICLR) 2025

Random-Set Neural Networks (RS-NN)

Shireen Kudukkil Manchingal, Muhammad Mubashar, Kaizheng Wang, Keivan Shariatmadar, Fabio Cuzzolin

Comments Published as a conference paper at the Thirteenth International Conference on Learning Representations (ICLR 2025)

Adversarial Mixup Unlearning

Zhuoyi Peng, Yixuan Tang, Yi Yang

Comments ICLR 2025

Exploring the Camera Bias of Person Re-identification

Myungseo Song, Jin-Woo Park, Jong-Seok Lee

Comments ICLR 2025 (Spotlight)

Realistic Evaluation of Deep Partial-Label Learning Algorithms

Wei Wang, Dong-Dong Wu, Jindong Wang, Gang Niu, Min-Ling Zhang, Masashi Sugiyama

Comments ICLR 2025 Spotlight

GEVRM: Goal-Expressive Video Generation Model For Robust Visual Manipulation

Hongyin Zhang, Pengxiang Ding, Shangke Lyu, Ying Peng, Donglin Wang

Comments Published as a conference paper at ICLR 2025

Data Center Cooling System Optimization Using Offline Reinforcement Learning

Xianyuan Zhan, Xiangyu Zhu, Peng Cheng, Xiao Hu, Ziteng He, Hanfei Geng, Jichao Leng, Huiwen Zheng, Chenhui Liu, Tianshun Hong, Yan Liang, Yunxin Liu, Feng Zhao

Comments Accepted in ICLR 2025

Preference Optimization for Reasoning with Pseudo Feedback

Fangkai Jiao, Geyang Guo, Xingxing Zhang, Nancy F. Chen, Shafiq Joty, Furu Wei

Comments 28 pages, 11 figures. ICLR 2025

MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs

Andreas Opedal, Haruki Shirakami, Bernhard Schölkopf, Abulhair Saparov, Mrinmaya Sachan

Comments ICLR 2025

Zero-shot Model-based Reinforcement Learning using Large Language Models

Abdelhakim Benechehab, Youssef Attia El Hili, Ambroise Odonnat, Oussama Zekri, Albert Thomas, Giuseppe Paolo, Maurizio Filippone, Ievgen Redko, Balázs Kégl

Journal ref The Thirteenth International Conference on Learning Representations (ICLR 2025)

Exploring Channel Distinguishability in Local Neighborhoods of the Model Space in Quantum Neural Networks

Sabrina Herbst, Sandeep Suresh Cranganore, Vincenzo De Maio, Ivona Brandic

Comments Published at ICLR 2025 (https://openreview.net/forum?id=gDcL7cgZBt)

Journal ref The Thirteenth International Conference on Learning Representations (2025)

CR-CTC: Consistency regularization on CTC for improved speech recognition

Zengwei Yao, Wei Kang, Xiaoyu Yang, Fangjun Kuang, Liyong Guo, Han Zhu, Zengrui Jin, Zhaoqing Li, Long Lin, Daniel Povey

Comments Published as a conference paper at ICLR 2025