FLARE: Diffusion for Hybrid Language Model

• URL: http://arxiv.org/abs/2606.01774v1
• Date: Mon, 01 Jun 2026 06:58:15 GMT
• Title: FLARE: Diffusion for Hybrid Language Model
• Abstract summary: FLARE is a systematic conversion framework for hybrid-attention large language models.<n>It combines a token-equal AR-and-diffusion objective, hardware-aware kernels, and unified inference, enabling one checkpoint to support both AR-style verified decoding and diffusion-style parallel denoising.<n>Our results suggest practical dLLMs are limited not only by decoding algorithms, but also by transfer data quality and the training inefficiency of current block-diffusion objectives.
• Score: 72.60770374799634
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment. Recent efficient-inference work has progressed along two axes: reducing the cost of each model invocation through efficient architectures, and reducing serial decoding steps through parallel generation. Hybrid attention backbones address the former, while diffusion language models (dLLMs) pursue the latter via iterative parallel denoising. Combining these advantages remains challenging: AR-to-dLLM conversion often fails to preserve seed-checkpoint capability, and hybrid-attention recurrent states and masking constraints make diffusion training and serving nontrivial. We present FLARE, a systematic conversion framework for hybrid-attention LLMs. Our analysis identifies transfer data quality as the primary determinant of capability preservation, outweighing loss formulation and attention-mask design. The resulting framework combines a token-equal AR-and-diffusion objective, hardware-aware kernels, and unified inference, enabling one checkpoint to support both AR-style verified decoding and diffusion-style parallel denoising. Starting from strong AR checkpoints with limited post-training data, FLARE is competitive with leading open-source dLLMs across model scales and delivers consistent throughput gains over open-source dLLM baselines in single-GPU concurrent serving. Our results further suggest that practical dLLMs are limited not only by decoding algorithms, but also by transfer data quality and the training inefficiency of current block-diffusion objectives, motivating joint design of data, objectives, architectures, and inference systems.

Related papers

• DARE: Diffusion Large Language Models Alignment and Reinforcement Executor [36.88819250898739]
  We present textbfDARE (textbfdLLMs textbfAlignment and textbfReinforcement textbfExecutor), an open framework for post-training and evaluating dLLMs.
  arXiv  Detail & Related papers  (2026-04-05T18:13:19Z)
• AsynDBT: Asynchronous Distributed Bilevel Tuning for efficient In-Context Learning with Large Language Models [4.4866154758274375]
  In-context learning (ICL) has emerged as a promising paradigm that enables LLMs to adapt to new tasks using examples provided within the input.<n>Previous FL approaches that incorporate ICL have struggled with severe straggler problems and challenges associated with heterogeneous non-identically data.<n>We propose an asynchronous distributed bilevel tuning (AsynDBT) algorithm that optimize both in-context learning samples and prompt fragments based on the feedback from the LLM.
  arXiv  Detail & Related papers  (2026-02-06T13:07:49Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• Causal Autoregressive Diffusion Language Model [70.7353007255797]
  CARD reformulates the diffusion process within a strictly causal attention mask, enabling dense, per-token supervision in a single forward pass.<n>Our results demonstrate that CARD achieves ARM-level data efficiency while unlocking the latency benefits of parallel generation.
  arXiv  Detail & Related papers  (2026-01-29T17:38:29Z)
• Auto-Regressive Masked Diffusion Models [9.239507801466322]
  Masked diffusion models (MDMs) have emerged as a promising approach for language modeling.<n>They face a performance gap compared to autoregressive models (ARMs) and require more training iterations.<n>We present the Auto-Regressive Masked Diffusion model, which unifies the training efficiency of autoregressive models with the parallel generation capabilities of diffusion-based models.
  arXiv  Detail & Related papers  (2026-01-23T18:42:30Z)
• Fast-dLLM v2: Efficient Block-Diffusion LLM [64.38006546510337]
  Fast-dLLM v2 is a block diffusion language model that adapts pretrained AR models into dLLMs for parallel text generation.<n>This represents a 500x reduction in training data compared to full-attention diffusion LLMs such as Dream (580B tokens)
  arXiv  Detail & Related papers  (2025-09-30T14:40:18Z)
• DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation [68.19756761027351]
  Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models.<n>We investigate their denoising processes and reinforcement learning methods.<n>Our work provides deeper insight into the machinery of dLLM generation and offers an effective, diffusion-native RL training framework.
  arXiv  Detail & Related papers  (2025-06-25T17:35:47Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.