x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability

• URL: http://arxiv.org/abs/2607.06114v2
• Date: Sat, 11 Jul 2026 13:56:34 GMT
• Title: x-Prediction Is All You Need:Training-Free Accelerated Generation via Endpoint Decodability
• Abstract summary: Diffusion and flow matching models generate high-quality samples, but their ODE samplers often need tens of hundreds of neural function evaluations (NFEs)<n>This remains a practical challenge for released checkpoints, since many accelerators require additional design choices and training cost through retraining, distillation, or trajectory redesign.<n>We investigate a different route based on $x$-prediction.<n>Across SDXL, SD3.5M, Z-Image-Turbo, and three class-conditional benchmarks, it reduces NFEs by 20--70% with near-matched quality.
• Score: 7.28668585578288
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion and flow matching models generate high-quality samples, but their ODE samplers often need tens to hundreds of neural function evaluations (NFEs). This remains a practical challenge for released checkpoints, since many accelerators require additional design choices and training cost through retraining, distillation, or trajectory redesign. We investigate a different route based on $x$-prediction. During sampling, standard affine probability paths already expose $x_0$ information: an intermediate state and its path velocity determine a principled estimate of the clean sample. We formalize this property as \textbf{endpoint decodability} and show that the decoder is the minimum-MSE estimator $\mathbb{E}[x_0\mid x_t]$ under the usual $\ell_2$ objective. This yields \textbf{Truncated Jump Sampling} (TJS): stop the ODE at an early-exit time $t^*$ and return the decoded $x_0$. TJS requires no retraining, distillation, or architecture change. Across SDXL, SD3.5M, Z-Image-Turbo, and three class-conditional benchmarks, it reduces NFEs by 20--70\% with near-matched quality. The analysis also shows why endpoint prediction can work without straightening the trajectory, providing inference acceleration without trajectory redesign.

Related papers

• Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors [51.56484100374058]
  Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against.<n>We train a single conditional latent diffusion model that steps a dynamical system forward or backward in time via a direction flag.<n>We show that this bidirectionality supplies a measurement-free test-time error signal.
  arXiv  Detail & Related papers  (2026-08-01T13:49:46Z)
• Three-Body Scattering for Generative Modeling [17.851305398372794]
  We show that a proper distributional energy can induce sample-level motion and provide direct regression supervision for a one-step generator.<n>Three-Body Scattering Modeling for generation turns the energy distance into a constant-size per-projectile interaction.<n>We provide a design map relating diffusion-related supervision, Drift-like dynamics, and GAN-like objectives.
  arXiv  Detail & Related papers  (2026-07-20T17:38:12Z)
• Velocity Scheduled Flow Matching [0.0]
  Flow matching trains a neural network to regress the conditional velocity along a linear interpolant between noise and data.<n>We introduce Velocity Scheduled Flow Matching, which replaces the conditional target.<n>VSFM can be sampled under any admissible profile by integrating its ODE on a non-uniform profile.
  arXiv  Detail & Related papers  (2026-07-13T11:50:06Z)
• Asymptotic-Preserving A Posteriori Analysis of Diffusion and Flow-Matching Samplers [0.6768558752130311]
  Diffusion and flow-matching samplers integrate a learned probability-flow ODE from a large noise scale down to a small terminal floor $_min$, at which the score is stiff and the flow develops a boundary layer.<n>We treat $_min$ as a singular-perturbation parameter and determine which fixed-step samplers are solvable.
  arXiv  Detail & Related papers  (2026-07-05T04:48:33Z)
• Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation [50.55853275866995]
  Real-time interactive video generation requires low-latency, streaming, and controllable rollout.<n>In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps.<n>We propose textbfCausal Forcing++, a principled and scalable pipeline.
  arXiv  Detail & Related papers  (2026-05-14T17:46:36Z)
• Post-Training with Policy Gradients: Optimality and the Base Model Barrier [27.674563695368665]
  We study post-training linear autoregressive models with outcome and process rewards.<n>We prove that variants of policy gradient (PG) can achieve likelihood $1 - varepsilon$ with an essentially minimax optimal number of reward queries.
  arXiv  Detail & Related papers  (2026-03-07T00:25:53Z)
• Meta Flow Maps enable scalable reward alignment [22.109809498990362]
  Controlling generative models is computationally expensive.<n>This is because optimal alignment with a reward function--whether via inference-time steering or fine-tuning--requires estimating the value function.<n>We introduce Meta Flow Maps (MFMs), a framework consistency models and flow maps into extending the regime.
  arXiv  Detail & Related papers  (2026-01-20T19:39:56Z)
• Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production [55.76222360698305]
  We explore a class of supervised training objectives that allow a language model to dynamically and autonomously scale the number of compute steps used for each input token.<n>For any token, the model can request additional compute steps by emitting a don't know> output.<n>We find that the CYB model requests additional steps when doing so improves accuracy, and the model adapts its processing time to token-level complexity and context.
  arXiv  Detail & Related papers  (2025-10-13T21:07:05Z)
• Simple ReFlow: Improved Techniques for Fast Flow Models [68.32300636049008]
  Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps. We propose seven improvements for training dynamics, learning and inference. We achieve state-of-the-art FID scores (without / with guidance, resp.) for fast generation via neural ODEs.
  arXiv  Detail & Related papers  (2024-10-10T11:00:55Z)
• Better Training of GFlowNets with Local Credit and Incomplete Trajectories [81.14310509871935]
  We consider the case where the energy function can be applied not just to terminal states but also to intermediate states. This is for example achieved when the energy function is additive, with terms available along the trajectory. This enables a training objective that can be applied to update parameters even with incomplete trajectories.
  arXiv  Detail & Related papers  (2023-02-03T12:19:42Z)
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction [63.41789556777387]
  Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP) We show that the number of samples needed to yield an entrywise $varepsilon$-accurate estimate of the Q-function is at most on the order of $frac1mu_min (1-gamma)5varepsilon2+ fract_mixmu_min (1-gamma)$ up to some logarithmic factor.
  arXiv  Detail & Related papers  (2020-06-04T17:51:00Z)

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.