Papers with dLLMs
Energy Matching based Preference Learning for Diffusion Language Models (2026.eacl-srw)
Copied to clipboard
| Challenge: | Existing methods for RL are not compatible with diffusion language models due to the difficulty of likelihood estimation. |
| Approach: | They propose a framework that reformulates KL-regularized RL as an energy-based distribution matching problem. |
| Outcome: | The proposed framework matches or surpasses the performance of diffu-GRPO and related baselines on multiple benchmarks in both online and offline setting. |
Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing cache eviction strategies for autoregressive language models fail to account for the role of mask tokens and specific characteristics in dLLMs. |
| Approach: | They propose a training-free cache eviction framework tailored to dLLMs that denies a fully masked sequence and allows parallel decoding at the expense of memory and computation. |
| Outcome: | The proposed framework reduces the cost of memory and cache eviction and improves efficiency by reducing allocation in intermediate layers and concentrating resources on prompt-preferring heads. |
Diffusion with Truncated Blocks: Fast and High-Quality Text Generation using Truncated Block Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Diffusion-based Large Language Models (dLLMs) generate text by iteratively denoising masked sequences. |
| Approach: | They propose a method that iteratively denoises masked sequences to reduce the model's attention dilution by token-level noise while models employing sequence-level noising exhibit a reduced effect. |
| Outcome: | The proposed method improves the performance and efficiency of Diffusion-based large language models by iterating on masked sequences. |
DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Autoregressive (AR) large audio language models are expensive in data and computation . prior work shows diffusion-based LALMs can improve audio understanding under matched settings . |
| Approach: | They propose a diffusion-based LALM that upgrades the speech encoder and employs dual semantic and acoustic adapters. |
| Outcome: | a new model improves over existing autoregressive large language models and is competitive to strong AR models . the proposed model can make use of limited training data and improve inference efficiency . a recent study shows that diffusion-based models can improve audio understanding . |
Pseudo-Likelihood Training for Reasoning Diffusion Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are the backbone of modern natural language processing and are powering applications ranging from code generation to autonomous agents. |
| Approach: | They propose a framework that uses pseudo-likelihood based objective for alignment of diffusion based language models (dLLMs). |
| Outcome: | The proposed method matches or surpasses dLLM training baselines on various coding and mathematical reasoning benchmarks. |
Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration (2026.acl-long)
Copied to clipboard
| Challenge: | Non-sequential and bidirectional nature of diffusion large language models makes direct likelihood-based self-evaluation challenging. |
| Approach: | They propose a self-evaluation confidence quantification method for diffusion large language models that quantifies confidence by computing the probability of regenerating tokens in the entire generated sequence, given the full context. |
| Outcome: | The proposed method is correlated with semantic coherence and answer accuracy. |
Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for reinforcement learning (RL) require a large sample size to be implemented. |
| Approach: | They propose a memory-efficient RL algorithm that maximizes a lower bound of the ELBO-based objective. |
| Outcome: | Experiments show that BGPO outperforms previous RL algorithms for diffusion large language models in math problem solving, code generation, and planning tasks. |
Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration (2026.findings-acl)
Copied to clipboard
Jucheng Shen, Gaurav Sarkar, Yeonju Ro, Sharath Nittur Sridhar, Zhangyang Wang, Aditya Akella, Souvik Kundu
| Challenge: | CadLLM is a plug-and-play model-agnostic with KV caching based dLLMs. |
| Approach: | They propose a lightweight adaptive method that can control the generation block size, step size, and threshold based on the average confidence score of unmasked tokens. |
| Outcome: | The proposed method can increase throughput by up to 1.1-2.28x over the state-of-the-art model with competitive accuracy. |
CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit (2026.acl-long)
Copied to clipboard
| Challenge: | Diffusion large language models generate text through iterative denoising with bidirectional attention, enabling richer contextual dependencies. |
| Approach: | They propose a training-free parallel decoding method that fuses Trace Credit with current logits to boost the confidence of correct but underconfident tokens. |
| Outcome: | The proposed method achieves 5.48 times speedup with +0.48 accuracy on LLaDA-8B and is orthogonal to mainstream inference optimizations. |
Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for estimating attention importance for tokens are ineffective . dLLMs require bidirectional attention, which limits inference efficiency . |
| Approach: | They propose a training-free attention sparsification framework for efficient long-context inference . they propose 'sink-aware pruning strategy' to accurately estimate and remove redundant computation . |
| Outcome: | The proposed approach offers 29 lossless speedup under 32K context length. |
Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | dLLMs have emerged as a promising non-autoregressive paradigm for text generation, but their hallucination mechanisms remain underexplored. |
| Approach: | They present the first controlled comparative study to evaluate hallucination patterns in Diffusion Large Language Models. |
| Outcome: | The proposed model exhibits higher propensity for hallucination than AR counterparts controlled for architecture, scale, and pre-training weights. |
Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Semi-autoregressive (Semi-AR) decoding suffers from inherent block constraints . naive lookahead decoding is unreliable, token stability closely correlates with convergence trend, and historical information is isolated. |
| Approach: | They propose a training-free, plug-and-play dynamic decoding strategy that monitors the stability of tokens in real time through dynamic anchors. |
| Outcome: | The proposed approach reduces decoding steps by 80% while improving performance by 3.67% on the BBH benchmark. |
d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models (2026.acl-long)
Copied to clipboard
Leyi Pan, Shuchang Tao, Yunpeng Zhai, Zheyu Fu, Liancheng Fang, Minghua He, Lingzhe Zhang, Zhaoyang Liu, Bolin Ding, Aiwei Liu, Lijie Wen
| Challenge: | Existing RL methods suffer from reliability bottlenecks due to reward sparsity and intractable computations . d-TreeRPO provides fine-grained and verifiable step-wise reward signals . |
| Approach: | They propose a reliable reinforcement learning framework for diffusion large language models that leverages tree-structured rollouts and bottom-up advantage computation based on verifiable outcome rewards. |
| Outcome: | The proposed framework outperforms baseline models and achieves significant improvements across reasoning benchmarks. |
Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Diffusion large language models (dLLMs) offer bidirectional attention and parallel generation . fixed anchors can enforce constraints, but they often impose rigid spans, leading to truncated reasoning . |
| Approach: | They propose a method that dynamically estimates end-anchor positions to adjust generation length before iterative infilling. |
| Outcome: | The proposed method improves format compliance and answer accuracy on GSM8K and MATH. |
TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing dLLMs rely on fixed denoising schedules and cannot learn efficient unmasking orders. |
| Approach: | They propose a framework that transforms dLLM decoding into a trajectory-aware policy . it uses a confidence-gated denoising strategy that decides which tokens to unmask . |
| Outcome: | The proposed model can learn which tokens to unmask and how many to unmak per step . it can learn the output quality and efficiency of the decoding path itself . |
AG-GRPO: Answer-Guided GRPO for Masked Diffusion Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent work on large language models (LLMs) has emphasized not only final-answer accuracy but also reliability of reasoning on challenging tasks. |
| Approach: | They propose an answer-guided group-relative policy optimization for masked diffusion language models which generates text through iterative mangled token restoration. |
| Outcome: | The proposed approach improves over pretrained dLLMs and prior RL methods across mathematics, puzzle-solving, and code-generation benchmarks. |
Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules (2026.findings-acl)
Copied to clipboard
| Challenge: | *SchED* is a training-free, model-agnostic early-exit algorithm that terminates diffusion decoding using a progress-aware confidence threshold. |
| Approach: | They propose a training-free, model-agnostic early-exit algorithm that terminates diffusion decoding using a progress-aware confidence threshold. |
| Outcome: | The proposed algorithm achieves 4 speedups on instruction-tuned models while maintaining baseline performance on average. |
The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check (2026.acl-long)
Copied to clipboard
| Challenge: | Embodied and Tool-Calling agents are effective in planning and complex reasoning, but require causal, precise, and logically grounded reasoning mechanisms to be viable for agentic tasks. |
| Approach: | They propose a framework that integrates dLLMs as plug-and-play cognitive cores. |
| Outcome: | The proposed model breaks the sequential latency bottleneck in agentic interactions. |
Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for full-attention dLLMs rely on random masking strategies that overlook intrinsic token dependencies. |
| Approach: | They propose an attention-guided denoising and optimization framework that aligns training and optimization with attention-derived dependencies. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on mathematical and coding benchmarks. |
Reinforcement Learning for Diffusion LLMs via Energy-Based Gibbs Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Diffusion Large Language Models (dLLMs) offer parallel decoding and bidirectional context modeling . aligning dLLms with reinforcement learning (RL) remains a challenge . |
| Approach: | They propose a variational framework that reformulates RL for dLLMs as a distribution matching problem. |
| Outcome: | The proposed framework reformulates RL for dLLMs as a distribution matching problem. |