FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency
arXiv:2506.08822v1 Announce Type: cross Abstract: Generative modeling-based visuomotor policies have been widely adopted in robotic manipulation attributed to their ability…
MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
arXiv:2506.07563v2 Announce Type: replace-cross Abstract: Personalized recommendation systems must adapt to user interactions across different domains. Traditional approaches like MLoRA…
Understanding Financial Reasoning in AI: A Multimodal Benchmark and Error Learning Approach
arXiv:2506.06282v1 Announce Type: new Abstract: Effective financial reasoning demands not only textual understanding but also the ability to interpret complex…
Distillation Robustifies Unlearning
arXiv:2506.06278v2 Announce Type: replace-cross Abstract: Current LLM unlearning methods are not robust: they can be reverted easily with a few…