HaloBlock introduces a difficulty‑aware adaptive halo mechanism for diffusion large language models (dLLMs) to address two inference challenges: decoding difficulty dominated by right‑side tokens and boundary contextual discontinuity in block‑wise decoding. By using bidirectional cumulative entropy to assess block difficulty, HaloBlock allocates halo regions on both sides of each block, smoothing cross‑block context propagation and reducing difficulty for hard tokens. Experiments on LLaDA‑8B‑Instruct, Dream‑7B‑Instruct, and LLaDA‑1.5 show consistent accuracy gains and faster convergence on mathematical reasoning and code generation tasks.
Diffusion large language models (DLLMs) enable non-autoregressive generation by iteratively denoising corrupted token sequences with bidirectional context. Despite their ability to update multiple positions in parallel, inference remains costly due to the many denoising steps required for high-quality generation.
arXiv:2605. 29233v2 Announce Type: replace-cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to strictly autoregressive decoding.
arXiv:2601. 22954v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel.
arXiv:2609.16450v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a promising parallel decoding paradigm as an alternative to autoregressive generation through iterative...
arXiv:2608. 13925v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) accelerate language generation by predicting multiple masks in a single forward pass.
arXiv:2607. 15655v1 Announce Type: cross Abstract: Masked diffusion language models (DLMs) enable parallel text generation by iteratively refining masked tokens, offering a promising alternative to autoregressive decoding.
arXiv:2606. 19475v1 Announce Type: new Abstract: Large Language Models (LLMs) have revolutionized language modeling through autoregressive generation, enabling strong performance across a wide range of tasks.
arXiv:2609.16372v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) generate text by iteratively denoising masked tokens with bidirectional attention. Extending reasoning across...
Ripple-Pivot Search (RPS) is a training‑free decoding method for Diffusion Large Language Models that identifies mid‑entropy pivot positions to reduce uncertainty across remaining masked tokens. By proactively committing these pivots and evaluating token assignments via lookahead, RPS enables more tokens to be unmasked in parallel, speeding up decoding. Experiments on three dLLMs and four reasoning/code‑generation benchmarks show 4–10× wall‑clock speedup over standard decoding, up to 18× with KV caching, while maintaining or improving generation quality.
arXiv:2608.22646v1 Announce Type: new Abstract: Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation...
arXiv:2606. 02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding.
The paper introduces Prefix-Block Policy Optimization (PBPO), a method that adapts block-level policy optimization to Diffusion Large Language Models (dLLMs). PBPO constructs a prefix-block state and uses a single model evaluation to create a factorized one‑step surrogate for block likelihood, allowing surrogate importance weighting and clipping to be applied separately to each token. Experiments on LLaDA-family models across six benchmarks and three generation lengths show that PBPO achieves competitive performance compared to existing dLLM reinforcement learning methods.