back to list
newsitem: ICLR 2025
We’re happy to present the following works at ICLR 2025:
main track (spotlight)
- Systems with Switching Causal Relations: A Meta-Causal Perspective
Moritz Willig, Tim Tobiasch, Florian Peter Busch, Jonas Seng, Devendra Singh Dhami, and Kristian Kersting - BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
Hikaru Shindo, Quentin Delfosse, Devendra Singh Dhami, and Kristian Kersting
main track
- Robust Transfer of Safety-Constrained Reinforcement Learning Agents
Markel Zubia, Thiago D. Simão, and Nils Jansen - Safety-Prioritizing Curricula for Constrained Reinforcement Learning
Cevahir Koprulu, Thiago D. Simão, Nils Jansen, Ufuk Popcu - HASARD: A Benchmark for Embodied Safe Reinforcement Learning
Tristan Tomilin, Meng Fang, and Mykola Pechenizkiy - RuAG: Learned-rule-augmented Generation for Large Language Models
Yudi Zhang, Pei Xiao, Lu Wang, Chaoyun Zhang, Meng Fang, Yali Du, Yevgeniy Puzyrev, Randolph Yao, Si Qin, Qingwei Lin, Mykola Pechenizkiy, Dongmei Zhang, Saravan Rajmohan, and Qi Zhang - Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustnes
Boqian Wu, Qiao Xiao, Shunxin Wang, Nicola Strisciuglio, Mykola Pechenizkiy, Maurice van Keulen, Decebal by Constantin Mocanu, and Elena Mocanu - Semantic Aware Representation Learning for Lifelong Learning
Fahad Sarfraz, Elahe Arani, and Bahram Zonooz - Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN
Pengxiang Li, Lu Yin, and Shiwei Liu - SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
Tianjin Huang, Ziquan Zhu, Gaojie Jin, Lu Liu, Zhangyang Wang, and Shiwei Liu