Looped Diffusion Language Models (LoopMDM): Depth Scaling via Layer Looping
LoopMDM introduces selective looping of early-middle transformer layers in masked diffusion language models, achieving a depth-scaling effect without adding parameters. The approach matches same-size MDM performance with up to 3.3× fewer training FLOPs and outperforms deeper non-looped MDMs on reasoning benchmarks, including up to 8.5 points improvement on GSM8K. Inference-time compute scaling is enabled by varying loop counts, with adaptive loop scheduling providing additional efficiency gains. Attention analysis suggests looping works by promoting interactions among masked token positions.
Related guides (4)
Related events (8)
Trajectory Analysis of Masked Diffusion LMs for Graph-to-Text Generation with Lambda-Scaled Structural Decoding
This paper presents the first systematic study of masked diffusion language models (MDLMs) for graph-to-text generation, analyzing the order in which tokens are unmasked during iterative decoding. The authors find MDLMs naturally unmask entities first, then relational/function words, then structural tokens—a pattern disrupted by supervised fine-tuning, which prematurely anchors structural tokens and causes hallucination or omission. They propose lambda-scaled structural decoding, a training-free inference-time fix that recovers +9.4 BLEU-4, and introduce Graph-LLaDA, which integrates a Graph Transformer encoder into LLaDA's decoding process. Cross-dataset evaluation on the LAGRANGE benchmark shows prior baselines overfit to dataset-specific patterns while MDLM-based approaches generalize better.
Looped World Models introduce iterative latent depth as a new scaling axis for world simulation
A new arXiv preprint introduces Looped World Models (LoopWM), a parameter-shared transformer architecture that iteratively refines latent environment states to achieve up to 100x parameter efficiency over conventional world models. The approach uses adaptive computation to scale depth dynamically per prediction step, addressing the tension between long-horizon simulation fidelity and deployment cost. The authors position iterative latent depth as a new scaling axis orthogonal to model size and training data.
SimSD: Speculative Decoding Adapted for Diffusion Language Models
SimSD introduces a training-free speculative decoding algorithm for diffusion large language models (dLLMs), which previously could not use standard token-level speculative decoding due to their bidirectional attention and masked language modeling formulation. The method uses a plug-and-play masking strategy that introduces reference tokens from a draft model and a custom attention mask, enabling valid logit computation for drafted tokens in a single forward pass. Evaluated on SDAR-family dLLMs across four benchmarks, SimSD achieves up to 7.46x decoding throughput improvement while maintaining or improving generation quality. The approach is compatible with other acceleration techniques such as KV cache and blockwise decoding.
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.
ADAS: Attention-Discounted Adaptive Sampler improves parallel decoding for masked diffusion language models
Researchers propose ADAS, a training-free reranking rule for masked diffusion language model decoding that addresses token interaction failures in parallel token commitment. The method greedily penalizes candidates that attend strongly to already-selected uncertain positions, using attention weights as soft marginal penalties rather than hard constraints. Evaluated on LLaDA-8B-Base and Dream-7B-Base across GSM8K, MATH500, HumanEval, and MBPP, ADAS improves low-NFE performance by 9–10 percentage points on average when plugged into existing samplers with only 3.1% runtime overhead.
LESS: Adaptive mutual-stability sampling cuts diffusion LLM decoding steps by 72%
Researchers introduce LESS, a training-free adaptive sampler for diffusion large language models that treats token commitment as an online stopping problem. The method uses a joint stability rule combining confidence, persistence, and distributional stability to decide when to unmask tokens, avoiding wasted computation on already-stable positions. Evaluated on Dream-7B, LLaDA-8B, and LLaDA-1.5-8B across seven benchmarks, LESS reduces reverse denoising steps by 72.1% versus fixed-budget decoding while improving accuracy over prior adaptive samplers. The step reductions translate directly to fewer Transformer forward passes and lower wall-clock latency.
RePlaid: Continuous Diffusion Language Models Scale Competitively with Discrete Diffusion
This paper revisits continuous diffusion language models (DLMs) by introducing RePlaid, an updated version of Plaid that aligns its architecture with modern discrete DLMs. RePlaid establishes the first scaling law for continuous DLMs competitive with discrete approaches, achieving a compute gap of only 20× versus autoregressive models and a state-of-the-art perplexity bound of 22.1 on OpenWebText among continuous DLMs. The authors provide theoretical analysis showing that likelihood-based training naturally yields linear cross-entropy over time and creates structured embedding geometries, explaining the performance gains.
SDXL in 4 Steps with Latent Consistency LoRAs
Hugging Face demonstrates combining Latent Consistency Models (LCMs) with LoRA adapters to enable high-quality image generation with Stable Diffusion XL in as few as 4 inference steps. This approach dramatically reduces the number of diffusion steps required compared to standard SDXL, lowering inference latency and compute cost. The technique leverages consistency distillation applied via lightweight LoRA weights, making it accessible without full model retraining.