Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models

• URL: http://arxiv.org/abs/2607.04461v1
• Date: Sun, 05 Jul 2026 19:02:32 GMT
• Title: Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models
• Abstract summary: Inference-time scaling for text-to-image generation has progressed from simple Best-of-$N$ sampling to guided search methods.<n>These approaches focus on when and how often to verify during denoising but largely treat the cost of generation itself as fixed.<n>We show that under wall-clock evaluation, simple BoN already matches or outperforms several guided search techniques.
• Score: 91.19049123903137
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inference-time scaling for text-to-image generation has progressed from simple Best-of-$N$ (BoN) sampling to guided search methods that verify and steer candidate trajectories at intermediate denoising steps. These approaches focus on when and how often to verify during denoising but largely treat the cost of generation itself as fixed. Moreover, the standard practice of comparing methods by number of function evaluations (NFEs) counts only denoising forward passes and ignores verifier overhead, which can distort efficiency rankings. We show that under wall-clock evaluation, simple BoN already matches or outperforms several guided search techniques, suggesting that compute is better spent on broader exploration than on repeated intermediate verification. This motivates Flash-BoN, which generates a large pool of inexpensive draft candidates by combining three complementary acceleration knobs: timestep truncation, layer skipping, and activation proxies into a single configuration optimized once per model. An efficient multi-stage verification procedure then identifies the most promising draft, which is refined at full quality. Across three benchmarks and three model scales, Flash-BoN consistently outperforms all baselines under fixed wall-clock budgets, with gains that grow at larger model scales (+8% AUC). We further show that our strategy combines well and improves existing orthogonal techniques such as reflection-based prompt optimization (+16% AUC). The gains correlate with increased candidate diversity, which also enables draft-guided selection to accelerate RL post-training convergence.

Related papers

• ZOMP: Zeroth-Order Multi-Modal Prompt Tuning for Vision-Language Models [14.64726819144383]
  ZOMP is a query-efficient, fully forward-only prompt-tuning method.<n>It consistently outperforms prior BP-free prompt-tuning methods in both few-shot accuracy and query efficiency.<n>Our results show that jointly exploiting multimodality and low-rank structure is an effective route to practical, practical BP-free prompt tuning.
  arXiv  Detail & Related papers  (2026-08-08T10:55:58Z)
• TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning [3.2829140652979647]
  Generative recommendation with Semantic IDs (SIDs) has emerged as a promising paradigm.<n>Existing methods apply a fixed inference strategy, either fast direct generation or slow chain-of-thought reasoning, uniformly across all user histories.<n>We propose Think Fast, Think Slow, Then Act, a framework that learns to adaptively allocate reasoning effort per user sequence.
  arXiv  Detail & Related papers  (2026-05-12T05:35:00Z)
• FASTER: Value-Guided Sampling for Fast RL [103.55398181003262]
  FASTER is a method for getting the benefits of sampling-based test-time scaling of diffusion-based policies without the computational cost.<n>FASTER achieves the same performance while substantially reducing training and inference compute requirements.
  arXiv  Detail & Related papers  (2026-04-21T17:52:17Z)
• $S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models [10.157422365382933]
  Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute.<n>We propose $S3$ (Stratified Scaling Search), a verifier-guided search method that improves generation by reallocating compute during the denoising process.<n>Experiments with LLaDA-8B-Instruct on MATH-500, GSM8K, ARC-Challenge, and TruthfulQA demonstrate that $S3$ consistently improves performance across benchmarks.
  arXiv  Detail & Related papers  (2026-04-07T00:51:06Z)
• LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion [87.42285185305813]
  We introduce a novel inference-time search mechanism that performs Reward-Guided Resampling and Pruning.<n>LatSearch consistently improves video generation across multiple evaluation dimensions compared to the baseline Wan2.1 model.
  arXiv  Detail & Related papers  (2026-03-15T18:07:29Z)
• 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)
• PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models [1.6816171955882597]
  PMPO locates low quality prompt segments via a masking based analysis and iteratively rewrites them to propose improved variants.<n>It selects among variants by minimizing loss in a single forward pass, eliminating output sampling and human or judge based scoring for selection.<n>Across model sizes and datasets, PMPO outperforms prior prompts: it achieves the highest average accuracy on BBH, performs strongly on GSM8K and AQUA RAT, and raises AlpacaEval 2.0 win rates by over 19 points.
  arXiv  Detail & Related papers  (2025-05-22T06:59:10Z)
• Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization [83.65278205301576]
  We propose to learn direct mappings from different noise levels to the optimal solution for a given instance, facilitating high-quality generation with minimal shots.<n>This is achieved through an optimization consistency training protocol, which minimizes the difference among samples.<n>Experiments on two popular tasks, the Traveling Salesman Problem (TSP) and Maximal Independent Set (MIS), demonstrate the superiority of Fast T2T regarding both solution quality and efficiency.
  arXiv  Detail & Related papers  (2025-02-05T07:13:43Z)
• Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment [81.84950252537618]
  This paper reveals a unified game-theoretic connection between iterative BOND and self-play alignment.<n>We establish a novel framework, WIN rate Dominance (WIND), with a series of efficient algorithms for regularized win rate dominance optimization.
  arXiv  Detail & Related papers  (2024-10-28T04:47:39Z)

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.