Momentum-Based Federated Reinforcement Learning with Interaction and Communication Efficiencyby Sheng Yue, Xingyuan Hua, Lili Chen,…
FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezingby Kai Huang, Haoming Wang,…
Repeat-Aware Neighbor Sampling for Dynamic Graph Learningby Tao Zou, Yuhao Mao, Junchen Ye, Bowen DuFirst…
How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations…
ReMoDetect: Reward Models Recognize Aligned LLM’s Generationsby Hyunseok Lee, Jihoon Tack, Jinwoo ShinFirst submitted to…
Dataset-learning duality and emergent criticalityby Ekaterina Kukleva, Vitaly VanchurinFirst submitted to arxiv on: 27 May…
The Expressive Capacity of State Space Models: A Formal Language Perspectiveby Yash Sarrof, Yana Veitsman,…
Transformers Can Do Arithmetic with the Right Embeddingsby Sean McLeish, Arpit Bansal, Alex Stein, Neel…
RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Controlby Litu Rout, Yujia Chen, Nataniel…
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Trainingby…