ICLR 2024 Conference Submissions

FireAct: Toward Language Agent Finetuning
Baian Chen, Chang Shu, Ehsan Shareghi, Nigel Collier, Karthik R Narasimhan, Shunyu Yao
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Vanishing Gradients in Reinforcement Finetuning of Language Models
Noam Razin, Hattie Zhou, Omid Saremi, Vimal Thilak, Arwen Bradley, Preetum Nakkiran, Joshua M. Susskind, Etai Littwin
- Published: 16 Jan 2024, Last Modified: 14 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications
Fengqing Jiang, Zhangchen Xu, Luyao Niu, Boxin Wang, Jinyuan Jia, Bo Li, Radha Poovendran
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
TCIG: Two-Stage Controlled Image Generation with Quality Enhancement through Diffusion
Salaheldin Mohamed
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Improving the efficiency of conformal predictors via test-time augmentation
Divya M Shanmugam, Helen Lu, Swami Sankaranarayanan, John Guttag
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Black-Box Privacy Attacks Against GANs via Detector Networks
Lukman Olagoke, Salil Vadhan, Seth Neel
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Grounding Language Plans in Demonstrations Through Counterfactual Perturbations
Yanwei Wang, Tsun-Hsuan Wang, Jiayuan Mao, Michael Hagenow, Julie Shah
- Published: 16 Jan 2024, Last Modified: 21 Apr 2024
- ICLR 2024 spotlight
- Readers: Everyone
Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty
Changbin Li, Kangshuo Li, Yuzhe Ou, Lance M. Kaplan, Audun Jøsang, Jin-Hee Cho, DONG HYUN JEONG, Feng Chen
- Published: 16 Jan 2024, Last Modified: 17 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Goodhart's Law in Reinforcement Learning
Jacek Karwowski, Oliver Hayman, Xingjian Bai, Klaus Kiendlhofer, Charlie Griffin, Joar Max Viktor Skalse
- Published: 16 Jan 2024, Last Modified: 15 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Score Regularized Policy Optimization through Diffusion Behavior
Huayu Chen, Cheng Lu, Zhengyi Wang, Hang Su, Jun Zhu
- Published: 16 Jan 2024, Last Modified: 15 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Conservative Prediction via Data-Driven Confidence Minimization
Caroline Choi, Fahim Tajwar, Yoonho Lee, Huaxiu Yao, Ananya Kumar, Chelsea Finn
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
3D Autoencoding Diffusion Model for Molecule Interpolation and Manipulation
Tianxiao Li, Martin Renqiang Min, Hongyu Guo, Mark Gerstein
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Robustifying and Boosting Training-Free Neural Architecture Search
Zhenfeng He, Yao Shu, Zhongxiang Dai, Bryan Kian Hsiang Low
- Published: 16 Jan 2024, Last Modified: 12 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Two Heads are Better than One: Towards Better Adversarial Robustness by Combining Transduction and Rejection
Nils Palumbo, Yang Guo, Xi Wu, Jiefeng Chen, Yingyu Liang, Somesh Jha
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Concept Bottleneck Generative Models
Aya Abdelsalam Ismail, Julius Adebayo, Hector Corrada Bravo, Stephen Ra, Kyunghyun Cho
- Published: 16 Jan 2024, Last Modified: 13 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling
Yaqing Wang, Jialin Wu, Tanmaya Dabral, Jiageng Zhang, Geoff Brown, Chun-Ta Lu, Frederick Liu, Yi Liang, Bo Pang, Michael Bendersky, Radu Soricut
- 23 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction Following
Renze Lou, Kai Zhang, Jian Xie, Yuxuan Sun, Janice Ahn, Hanzi Xu, Yu Su, Wenpeng Yin
- Published: 16 Jan 2024, Last Modified: 15 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Latent Consistency Models: Synthesizing High-Resolution Images with Few-step Inference
Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, Hang Zhao
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
Bochuan Cao, Yuanpu Cao, Lu Lin, Jinghui Chen
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Reconstruction of Cortical Surfaces with Spherical Topology from Infant Brain MRI via Recurrent Deformation Learning
Xiaoyang Chen, Junjie Zhao, Siyuan Liu, Sahar Ahmad, Pew-Thian Yap
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
DLCNet: Enabling Long-Range Convolution with Data Dependency
Qingyu Yin, Xiang Zhuang, Keyan Ding, Qiang Zhang
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
On Memorization in Diffusion Models
Xiangming Gu, Chao Du, Tianyu Pang, Chongxuan Li, Min Lin, Ye Wang
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Sparse-Guard: Sparse Coding-Based Defense against Model Inversion Attacks
Sayanton V. Dibbo, Adam Breuer, Juston Moore, Michael Teti
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Discovering Mathematical Formulas from Data via LSTM-guided Monte Carlo Tree Search
Yanjie Li, Weijun Li, Lina Yu, Min Wu, Linjun Sun, Jingyi Liu, Wenqiang Li, Meilan Hao
- 23 Sept 2023 (modified: 29 Jan 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Weakly Supervised Graph Contrastive Learning
Pratheeksha Nair, Reihaneh Rabbany
- 23 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone