paper-with-me

Papers

Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization

2025-10-09 · Kevin Rojas, Jiahe Lin, Kashif Rasul, Anderson Schneider, Yuriy Nevmyvaka, Molei Tao, Wei Deng arxiv

Diffusion language models (DLMs) enable parallel, order-agnostic generation with iterative refinement, offering a flexible alternative to autoregressive large language models (LLMs). However, adapting reinforcement learning (RL) fine-tuning to DLMs remains an open challenge because of the intractable likelihood. Pioneering work such as diffu-GRPO estimated token-level likelihoods via one-step unmasking. While computationally efficient, this approach is severely biased. A more principled foundation lies in sequence-level likelihoods, where the evidence lower bound (ELBO) serves as a surrogate. Yet, despite this clean mathematical connection, ELBO-based methods have seen limited adoption due to the prohibitive cost of likelihood evaluation. In this work, we revisit ELBO estimation and disentangle its sources of variance. This decomposition motivates reducing variance through fast, deterministic integral approximations along a few pivotal dimensions. Building on this insight, we introduce Group Diffusion Policy Optimization (GDPO), a new RL algorithm tailored for DLMs. GDPO leverages simple yet effective Semi-deterministic Monte Carlo schemes to mitigate the variance explosion of ELBO estimators under vanilla double Monte Carlo sampling, yielding a provably lower-variance estimator under tight evaluation budgets. Empirically, GDPO achieves consistent gains over pretrained checkpoints and outperforms diffu-GRPO, one of the state-of-the-art baselines, on the majority of math, reasoning, and coding benchmarks.

📄 PDF Abstract BibTeX arXiv:2510.08554

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Simple Policy Gradients for Reasoning with Diffusion Language Models

2025-10-05 · Anthony Zhan arxiv

Diffusion large language models (dLLMs) represent a promising alternative to autoregressive LLMs; however, the lack of effective post-training techniques, including reinforcement learning (RL), remains a key challenge fo…

Reinforcement Learning

Empathetic Motion Generation for Humanoid Educational Robots via Reasoning-Guided Vision--Language--Motion Diffusion Architecture

2026-03-19 · Fuze Sun, Lingyu Li, Lekan Dai, Xinyu Fan arxiv

This article suggests a reasoning-guided vision-language-motion diffusion framework (RG-VLMD) for generating instruction-aware co-speech gestures for humanoid robots in educational scenarios. The system integrates multi-…

Motion Synthesis

Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models

2025-05-15 · Zemin Huang, Zhiyang Chen, Zijun Wang, Tiancheng Li 외

We introduce the Diffusion Chain of Lateral Thought (DCoLT), a reasoning framework for diffusion language models. DCoLT treats each intermediate step in the reverse diffusion process as a latent "thinking" action and opt…

Code GenerationGSM8KHumanEvalMath+2

Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models

2025-10-03 · Tianren Ma, Mu Zhang, Yibing Wang, Qixiang Ye arxiv

Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group…

Reinforcement Learning

Diffusion-GR2: Diffusion Generative Reasoning Re-ranker

2026-07-01 · Zhuoxuan Zhang, Kangqi Ni, Yuhang Chen, Mingfu Liang 외 arxiv

Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering a candidate list, but they are slow at inference: an autoregressive (AR) decoder spends one sequent…