EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation

• URL: http://arxiv.org/abs/2602.07967v1
• Date: Sun, 08 Feb 2026 13:29:46 GMT
• Title: EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
• Abstract summary: We propose EasyTune, which fine-tunes diffusion at each denoising step rather than over the entire trajectory.<n>We also introduce a Self-refinement Preference Learning mechanism that dynamically identifies preference pairs and conducts preference learning.<n>Experiments demonstrate that EasyTune outperforms DRaFT-50 by 8.2% in alignment (MM-Dist) improvement.
• Score: 6.674252840296312
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, motion generative models have undergone significant advancement, yet pose challenges in aligning with downstream objectives. Recent studies have shown that using differentiable rewards to directly align the preference of diffusion models yields promising results. However, these methods suffer from (1) inefficient and coarse-grained optimization with (2) high memory consumption. In this work, we first theoretically and empirically identify the key reason of these limitations: the recursive dependence between different steps in the denoising trajectory. Inspired by this insight, we propose EasyTune, which fine-tunes diffusion at each denoising step rather than over the entire trajectory. This decouples the recursive dependence, allowing us to perform (1) a dense and fine-grained, and (2) memory-efficient optimization. Furthermore, the scarcity of preference motion pairs restricts the availability of motion reward model training. To this end, we further introduce a Self-refinement Preference Learning (SPL) mechanism that dynamically identifies preference pairs and conducts preference learning. Extensive experiments demonstrate that EasyTune outperforms DRaFT-50 by 8.2% in alignment (MM-Dist) improvement while requiring only 31.16% of its additional memory overhead and achieving a 7.3x training speedup. The project page is available at this link {https://xiaofeng-tan.github.io/projects/EasyTune/index.html}.

Related papers

• Scaling Reinforcement Learning for Diffusion Models via Velocity Matching [66.34541945134916]
  RewardBench fine-tuning is an important tool for adapting diffusion models to human preferences and task-specific objectives.<n>Unlike autoregressive models, diffusion models do not provide tractable likelihoods for generated samples.<n>We propose reward-based velocity matching (RVM), a simple trajectory-free update that acts directly on the velocity field.
  arXiv  Detail & Related papers  (2026-08-24T17:13:43Z)
• PAST: Prompt-Adaptive Sampling Termination for Efficient Diffusion Model [11.180362540642689]
  PAST enhances computational efficiency of existing RL fine-tuning methods by up to 66.7%.<n>It also improves preference optimization quality by up to 29.5% through its dual adaptive regulation mechanism.
  arXiv  Detail & Related papers  (2026-08-07T04:35:26Z)
• Self-Adversarial One Step Generation via Condition Shifting [11.426065945265647]
  APEX is a framework for adversarial correction signals extracted endogenously from a flow model.<n>Our 0.6B model surpasses FLUX-Schnell 12B (20$times$ more parameters) in one step quality.<n>With LoRA tuning on Qwen-Image 20B, APEX reaches a GenEval score of 0.89 at NFE=1 in 6 hours, surpassing the original 50-step teacher (0.87) and providing a 15.33$times$ inference speedup.
  arXiv  Detail & Related papers  (2026-04-14T05:54:33Z)
• MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation [36.11192536249353]
  We present a reinforcement fine-tuning framework for text-to-motion generative models.<n> MotionReward maps heterogeneous motions into a shared semantic space anchored by text.<n>Self-refinement Preference Learning enhances semantics without additional annotations.<n>Experiments validate the effectiveness of our framework, achieving FID 0.132 at 22.10 GB peak memory for MLD model and saving up to 15.22 GB over DRaFT.
  arXiv  Detail & Related papers  (2026-03-28T08:10:53Z)
• MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving [23.013043338076745]
  MeanFuser is an end-to-end autonomous driving method.<n>We introduce GMN to guide generative sampling and adapt MeanFlow Identity" to end-to-end planning.<n>Experiments on the NAVSIM closed-loop benchmark demonstrate that MeanFuser achieves outstanding performance without the supervision of the PDM Score.
  arXiv  Detail & Related papers  (2026-02-23T17:17:26Z)
• Symmetry Breaking in Transformers for Efficient and Interpretable Training [5.624886369964602]
  We introduce a simple symmetry-breaking protocol that inserts a preferred direction into a rotational space through batchwise-sampled, unlearned query and value biases.<n>First, it can substantially improve the performance of simple, memory-efficients.<n>Second, it enables an interpretable use of otherwise redundant rotational degrees of freedom.
  arXiv  Detail & Related papers  (2026-01-29T19:29:09Z)
• 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)
• Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration [42.60904284683844]
  We propose a framework that decomposes the token reduction into three stages: filtering redundant tokens, correlating discarded information to preserved tokens, and compressing tokens to minimize redundancy.<n>FiCoCo achieves up to 5.7x/14.7x FLOPs reduction with 92.8%/93.6% performance retention on LLaVA-1.5-7B/LLaVA-NeXT-7B.
  arXiv  Detail & Related papers  (2024-11-26T18:53:51Z)
• DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization [22.546989373687655]
  We propose a novel pruning method that derives an efficient diffusion model via a more intelligent and differentiable pruner. Our approach achieves 4.4 x speedup for SD-1.5 without any loss of accuracy, significantly outperforming the previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-22T12:18:24Z)
• Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers [35.57237027659979]
  Mixture of Depths (MoD) dynamically adjust the computational depth by skipping less important layers.<n>MoD approaches face two main challenges: (1) high training costs due to the need to train the entire model along with the routers that determine which layers to skip, and (2) the risk of performance degradation when important layers are bypassed.<n>We propose Router-Tuning, a method that fine-tunes only the router on a small dataset, drastically reducing the computational overhead associated with full model training.<n>For the second challenge, we propose MindSkip, which deploys Attention with Dynamic Depths.
  arXiv  Detail & Related papers  (2024-10-17T03:23:50Z)
• Diffusion Models as Optimizers for Efficient Planning in Offline RL [47.0835433289033]
  Diffusion models have shown strong competitiveness in offline reinforcement learning tasks. We propose a faster autoregressive model to handle the generation of feasible trajectories. This allows us to achieve more efficient planning without sacrificing capability.
  arXiv  Detail & Related papers  (2024-07-23T03:00:01Z)
• The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling [78.6155095947769]
  Skip-Tuning is a simple yet surprisingly effective training-free tuning method on the skip connections. Our method can achieve 100% FID improvement for pretrained EDM on ImageNet 64 with only 19 NFEs (1.75) While Skip-Tuning increases the score-matching losses in the pixel space, the losses in the feature space are reduced.
  arXiv  Detail & Related papers  (2024-02-23T08:05:23Z)
• SinSR: Diffusion-Based Image Super-Resolution in a Single Step [119.18813219518042]
  Super-resolution (SR) methods based on diffusion models exhibit promising results. But their practical application is hindered by the substantial number of required inference steps. We propose a simple yet effective method for achieving single-step SR generation, named SinSR.
  arXiv  Detail & Related papers  (2023-11-23T16:21:29Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)
• Fine-Tuning Language Models with Just Forward Passes [92.04219196752007]
  Fine-tuning language models (LMs) has yielded success on diverse downstream tasks, but as LMs grow in size, backpropagation requires a large amount of memory. We propose a memory-efficient zerothorder (MeZO) to operate in-place, thereby fine-tuning LMs with the same memory footprint as inference.
  arXiv  Detail & Related papers  (2023-05-27T02:28:10Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.