EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learningby Syed Irfan Ali Meerza,…
Investigating on RLHF methodologyby Alexey Kutalev, Sergei MarkoffFirst submitted to arxiv on: 2 Oct 2024CategoriesMain:…
Learning To Solve Differential Equation Constrained Optimization Problemsby Vincenzo Di Vito, Mostafa Mohammadian, Kyri Baker,…
NEAT: Nonlinear Parameter-efficient Adaptation of Pre-trained Modelsby Yibo Zhong, Haoxiang Jiang, Lincan Li, Ryumei Nakada,…
VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignmentby Amirhossein Kazemnejad, Milad Aghajohari,…
LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Banditsby Duy Nguyen, Archiki Prasad, Elias…
PreND: Enhancing Intrinsic Motivation in Reinforcement Learning through Pre-trained Network Distillationby Mohammadamin Davoodabadi, Negin Hashemi…
Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?by Xi Chen, Kaituo Feng,…
In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasksby Dingzirui Wang, Xuanliang Zhang, Qiguang Chen,…
Fair Class-Incremental Learning using Sample Weightingby Jaeyoung Park, Minsu Kim, Steven Euijong WhangFirst submitted to…