SDGD uses cost-conditioned classifier-free guidance plus reward guidance with feasible trajectory relabeling to generate safe high-reward trajectories that adapt to changing safety budgets in offline RL.
Efficient planning with latent diffusion.arXiv preprint arXiv:2310.00311
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A 4D latent predictive model encodes scenes holistically to generate 3D-consistent futures that an inverse dynamics module converts into robot actions, outperforming video-based planners on manipulation tasks.
Conditional Graph Diffusion generates continuous negotiation outcomes with high individual rationality using GATv2 encoders, cross-attention fusion, and inference-time normative guidance gradients.
citing papers explorer
-
Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
SDGD uses cost-conditioned classifier-free guidance plus reward guidance with feasible trajectory relabeling to generate safe high-reward trajectories that adapt to changing safety budgets in offline RL.
-
Structured 4D Latent Predictive Model for Robot Planning
A 4D latent predictive model encodes scenes holistically to generate 3D-consistent futures that an inverse dynamics module converts into robot actions, outperforming video-based planners on manipulation tasks.
-
Conditional Graph Diffusion for Negotiation Support: Overcoming Discrete Infeasibility and Preference Elicitation Gaps
Conditional Graph Diffusion generates continuous negotiation outcomes with high individual rationality using GATv2 encoders, cross-attention fusion, and inference-time normative guidance gradients.