DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
Simple statistical gradient-following algorithms for connectionist reinforcement learning.Machine learning, 8(3):229–256
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Certain errors in proxy rewards for policy gradient methods can be benign or beneficial by preventing policies from stalling on outputs with mediocre ground truth rewards, enabling improved RLHF metrics and reward design insights.
Sol-RL decouples FP4-based candidate exploration from BF16 policy optimization in diffusion RL, delivering up to 4.64x faster convergence with maintained or superior alignment performance on models like FLUX.1 and SD3.5.
MDPO improves differentiable planning by injecting gradient-sensitivity-adapted noise into the action space, outperforming both deterministic variants and PPO on nonlinear and hybrid benchmarks.
citing papers explorer
-
Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
-
When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient
Certain errors in proxy rewards for policy gradient methods can be benign or beneficial by preventing policies from stalling on outputs with mediocre ground truth rewards, enabling improved RLHF metrics and reward design insights.
-
FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling
Sol-RL decouples FP4-based candidate exploration from BF16 policy optimization in diffusion RL, delivering up to 4.64x faster convergence with maintained or superior alignment performance on models like FLUX.1 and SD3.5.
-
Model-Driven Policy Optimization in Differentiable Simulators via Stochastic Exploration
MDPO improves differentiable planning by injecting gradient-sensitivity-adapted noise into the action space, outperforming both deterministic variants and PPO on nonlinear and hybrid benchmarks.