4arXiv cs.AI (Artificial Intelligence)·
DADiff: Diffusion-based framework for cross-domain policy adaptation in reinforcement learning
DADiff is a new diffusion-based framework for online dynamics adaptation in reinforcement learning, addressing the domain transfer problem by leveraging discrepancies between source and target domain generative trajectories during next-state prediction. The authors develop both reward modification and data selection variants, and provide theoretical bounds on policy performance differences in terms of generative trajectory deviation. Experiments across environments with various domain shifts show superior performance over existing approaches. Code is publicly released.
Related guides (1)
Related events (8)
Ambient Diffusion Policy: imitation learning from suboptimal robot data via noise-dependent co-training
Researchers introduce Ambient Diffusion Policy, a method for robot imitation learning that extracts useful features from suboptimal demonstrations by restricting their contribution to specific diffusion timesteps (high and low noise levels). The approach is grounded in the observation that robot action data follows a spectral power law, inducing global-to-local hierarchy and locality properties in diffusion models. Evaluated across six tasks and four types of suboptimal data, it outperforms co-training baselines by up to 33% when scaled to the Open X-Embodiment dataset.
Finetune Stable Diffusion Models with DDPO via TRL
Hugging Face's TRL library adds support for DDPO (Denoising Diffusion Policy Optimization), enabling reinforcement learning-based finetuning of Stable Diffusion models. This extends TRL's RLHF tooling beyond language models to image generation, allowing reward-driven optimization of diffusion models. The post demonstrates practical usage of the new DDPO trainer within the TRL ecosystem.
DRPO: Smooth divergence regularization replaces hard masking in LLM RL training
A new arXiv preprint proposes Divergence Regularized Policy Optimization (DRPO), a method that replaces the hard trust-region mask used in DPPO with a smooth advantage-weighted quadratic regularizer on policy shift. The approach addresses a known weakness in PPO and GRPO where importance ratios poorly proxy distributional shift in long-tailed vocabularies, and in DPPO where gradient signals are discarded rather than corrected at trust-region boundaries. Experiments across model scales, architectures, and precision settings show improved stability and efficiency in LLM RL post-training.
d-OPSD: First on-policy self-distillation framework tailored for diffusion LLMs
Researchers introduce d-OPSD, the first on-policy self-distillation (OPSD) framework designed specifically for diffusion large language models (dLLMs). The method addresses a fundamental mismatch between existing autoregressive OPSD approaches and dLLMs' arbitrary-order generation by using suffix conditioning on self-generated answers and step-level rather than token-level divergence supervision. Across four reasoning benchmarks, d-OPSD outperforms RLVR and SFT baselines while requiring only ~10% of the optimization steps of RLVR, suggesting strong sample efficiency gains for dLLM post-training.
Mask-Aware Policy Gradients improve RL training for Masked Diffusion Language Models
A new arXiv preprint introduces a two-stage action MDP formalization for applying reinforcement learning to Masked Diffusion Language Models (MDLMs), decomposing the policy gradient into a token prediction term and a masking order term. Prior approaches ignored the position-unmasking decision, leading to intractable log-likelihood estimates; the proposed method optimizes both terms jointly. The approach achieves 87.1% on GSM8K and 53.4% on MBPP, claiming state-of-the-art results for MDLM-based reasoning and coding.
AGDO: Attention-guided denoising and optimization framework improves diffusion language model reasoning
Researchers propose AGDO, a framework that replaces random masking in diffusion large language models (dLLMs) with attention-guided denoising order and token weighting during fine-tuning and reinforcement learning. The work is motivated by an empirical finding that tokens with stronger attention to unmasked context are more stable and critical for reasoning. Experiments on math and coding benchmarks show AGDO outperforms existing post-training methods for dLLMs, advancing the case for attention-aware training in parallel-decoding language models.
Kolmogorov Regression lifts diffusion policies to Cameron-Martin space for robust long-horizon control
Researchers introduce a backward Kolmogorov equation framework that reformulates diffusion policy training as a deterministic boundary-value PDE problem in Cameron-Martin space, replacing stochastic score matching. The approach uses a precision-weighted Cameron-Martin loss and a Kolmogorov residual as an inference-time failure detector, yielding convergence guarantees tied to kernel effective rank rather than action dimension. Validation on the PushT manipulation benchmark shows 17% improvement in episode reward and 67.6% reduction in inter-step drift; a 6-station manufacturing scheduling task shows 28.4% lower RMSE than LSTM baselines and 96% reduction in deadlock events via Hamilton-Jacobi reachability certification.
SARDI: Self-Augmenting Retrieval for Diffusion Language Models using lookahead tokens
Researchers introduce SARDI, a training-free RAG framework for discrete diffusion language models that repurposes discarded low-confidence tokens during denoising as lookahead signals to guide retrieval before output is finalized. The method is retriever-agnostic and applicable to any reasoning-capable discrete diffusion LM. Evaluated across five multi-hop QA benchmarks, SARDI outperforms training-free diffusion and autoregressive retrieval baselines at up to 8x higher throughput.