2 papers
cs.LG2026
Improving Diffusion Planners by Self-Supervised Action Gating with Energies
Yuan Lu, Dongqi Han, Yansen Wang +1
Diffusion planners are a strong approach for offline reinforcement learning, but they can fail when value-guided selection favours trajectories that score well yet are locally inco…
cs.LG2026
Dispelling the Curse of Singularities in Neural Network Optimizations
Hengjie Cao, Mengyi Chen, Yifeng Yang +11
This work investigates the optimization instability of deep neural networks from a less-explored yet insightful perspective: the emergence and amplification of singularities in the…