Informed Masking (IM) is a new technique for aligning Diffusion Large Language Models (dLLMs) with Reinforcement Learning (RL). It identifies a systematic upstream/downstream token structure in dLLM rollouts and shows that masking downstream tokens creates better subproblems for likelihood estimation. When integrated into three state‑of‑the‑art dLLM RL methods on LLaDA‑8B‑Instruct, IM yields up to 2.01%, 8.68%, and 5.77% relative average gains on math and planning benchmarks while improving training stability.
By Xiaoyi Yu, Enver Sangineto, Pei Fu, Fiorenzo Parascandolo, Wenhui Tan, Ruikang Zhang, Rita Cucchiara, Ruihua Song, Jian Luan
SP$^2$ec is a training‑free bandit algorithm that adapts the draft configuration during generation for Vision‑Language Models, exploiting a single‑peak throughput pattern observed in existing self‑speculative methods. It minimizes a novel wall‑time regret metric, theoretically guaranteeing near‑optimal draft selection with negligible exploration cost. Experiments on Qwen2.5‑VL‑7B‑Instruct and LLaVA‑Next‑Mistral‑7B show consistent improvements of up to 11% over prior self‑speculative methods across visual and textual tasks.
By Yuqi Huang, Xingyao Li, Yunlong Hou, Fengzhuo Zhang, Jiachun Pan, Vincent Y. F. Tan
arXiv:2609.36202v1 Announce Type: cross
Abstract: Gradient-based reward guidance provides a flexible way to use downstream reward models to control masked diffusion language models at inference time....
By Darshan Thaker, Lachlan Ewen MacDonald, Ren\'e Vidal
arXiv:2607. 15200v1 Announce Type: cross Abstract: Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs) remains challenging due to the intractability of the log-likelihood estimation.
By Haran Raajesh, Kulin Shah, Adam Klivans, Philipp Kr\"ahenb\"uhl
arXiv:2609.37974v1 Announce Type: cross
Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...
By Manuel Madeira, Amitis Shidani, Alice Bizeul, Victor Turrisi, Louis B\'ethune, Bhavika Devnani, Dan Busbridge, Pierre Ablin, Jo\~ao Monteiro
The paper introduces TIPS, a tiny inference-time policy that controls which tokens are visible during each denoising pass of masked diffusion language models. TIPS, a 600‑K‑parameter shallow transformer, learns to unmask and remask tokens while keeping the language model frozen, using visibility‑aware confidence features and a fixed schedule for expected visibility. Trained via supervised warmup and reinforcement learning, TIPS achieves over 58% accuracy on GSM8K and MATH‑500 with only 32 decoder evaluations, surpassing strong baselines by more than 11 percentage points and remaining competitive at higher budgets without retraining.
By Ya-Shi Zhang, Jian Tang, Pierre-Andr\'e No\"el, Oleksiy Ostapenko
arXiv:2610.17266v1 Announce Type: new
Abstract: Diffusion language models are a promising and more efficient alternative to autoregressive models. However, most RL post-training techniques are not ea...
By Vaibhav Singh, Eugene Belilovsky
arXiv:2607. 08837v1 Announce Type: cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers.
By Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identical rollout rewards consume generation budget without effective learning signals. Pre-rollout prompt selection can reduce this waste by screening prompts before rollout generation.
arXiv:2607.28077v2 Announce Type: replace
Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identica...
By Shuang Liang, Haoyang Zhou, Yifan Gong, Guowei Wang, Xiting Wang
arXiv:2607.08837v4 Announce Type: replace-cross
Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject...
By Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong
arXiv:2607. 09015v1 Announce Type: cross Abstract: We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large language model (LLM) routing.
By Ajay Narayanan Sridhar, Ronak Singh, Mehrdad Mahdavi, Vijaykrishnan Narayanan