Temporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video Diffusion

• URL: http://arxiv.org/abs/2607.28058v1
• Date: Thu, 30 Jul 2026 11:36:48 GMT
• Title: Temporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video Diffusion
• Abstract summary: temporally sparse artifacts such as motion collapse, object flickering, and color oversaturation remain a major barrier to perceptual realism.<n>Existing methods struggle with these issues due to two key limitations.<n>We propose concentrated Implicit Preference Optimization (cIPO), a post-training framework for video diffusion models.
• Score: 33.237232061796796
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in preference alignment for diffusion-based video generation, particularly via Direct Preference Optimization (DPO), have significantly improved visual quality. However, temporally sparse artifacts such as motion collapse, object flickering, and color oversaturation remain a major barrier to perceptual realism. Existing methods struggle with these issues due to two key limitations: (1) the preference attribution bottleneck, where offline human annotations are costly and fail to accurately capture learning dynamics, while online reward signals are rollout-aware but often unstable and biased; and (2) temporal credit misallocation, where uniformly applied supervision cannot effectively target the brief segments in which artifacts occur. To address these challenges, we propose concentrated Implicit Preference Optimization (cIPO), a post-training framework for video diffusion models. cIPO derives implicit preference signals directly from the denoising process: given a real video, the model adds forward noise and reconstructs it via iterative denoising, treating the original as the preferred sample and the reconstruction as the dispreferred one. This formulation captures inference-time errors without requiring human annotations or external reward models. Moreover, frame-level discrepancies between original and reconstructed videos reveal when failures occur. cIPO leverages this by computing temporal reconstruction errors and concentrating optimization on high-error segments, enabling more precise correction of failure-prone regions. Extensive experiments demonstrate that cIPO consistently enhances video authenticity and temporal coherence across multiple datasets, highlighting the effectiveness and efficiency of implicit preference with temporally concentrated optimization.

Related papers

• P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization [55.74731799669337]
  Hallucination has recently garnered significant research attention in Large Vision-Language Models (LVLMs)<n>Direct Preference Optimization (DPO) aims to learn directly from the corrected preferences provided by humans.<n>Existing preference pairs are often vision-agnostic and their inherently off-policy nature limits their effectiveness in guiding model learning.<n>We propose Perceptual Processing Direct Preference Optimization (P$2$-DPO), a novel training paradigm in which the model generates and learns from its own preference pairs.
  arXiv  Detail & Related papers  (2026-06-02T09:22:53Z)
• Temporal Aware Pruning for Efficient Diffusion-based Video Generation [22.469564305396002]
  We propose TAPE, a training-free Temporal Aware for Efficient diffusion-based video generation.<n>We show that TAPE delivers significant speedups while preserving high visual fidelity, outperforming prior token reduction approaches.
  arXiv  Detail & Related papers  (2026-05-18T04:18:24Z)
• SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning [17.14027883239169]
  We propose a post-training framework SyncDPO to improve the temporal sensitivity of V-A joint generation.<n>We demonstrate that SyncDPO significantly outperforms other methods in improving model's temporal alignment capability.
  arXiv  Detail & Related papers  (2026-05-12T14:22:13Z)
• CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating [49.94171749437024]
  We propose Concentrate and Concentrate (CaC), a coarse-to-fine anomaly reward model based on Vision-Language Models.<n>We construct the first largescale generated video anomaly dataset with per-frame bounding-box annotations, temporal anomaly windows, and fine-grained attribution labels.<n>In experiments, CaC can stably concentrate on subtle anomalies, achieving a 25.7% accuracy improvement on fine-grained anomaly benchmarks.
  arXiv  Detail & Related papers  (2026-05-12T08:08:33Z)
• Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers [12.948398661304184]
  Diffusion-APO is a trajectory-aware algorithm for aligning video diffusion models with human intent.<n>We introduce a unified and modular RLHF framework that integrates online ranking, half-online anchoring, offline refinement, and distillation-aware drift correction.<n>We demonstrate that Diffusion-APO consistently outperforms standard baselines in visual quality and instruction following.
  arXiv  Detail & Related papers  (2026-05-08T09:37:46Z)
• CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models [66.56549019393042]
  Video-language models (VLMs) achieve strong multimodal understanding but remain prone to hallucinations, especially when reasoning about actions and temporal order.<n>We propose a scalable framework for counterfactual video generation that synthesizes videos differing only in actions or temporal structure while preserving scene context.
  arXiv  Detail & Related papers  (2026-01-08T10:03:07Z)
• Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models [65.16788152626499]
  LocalDPO builds a novel framework for aligning video diffusion models with human preferences.<n>We show that LocalDPO consistently improves video fidelity, temporal coherence and human preference scores over other post-training approaches.
  arXiv  Detail & Related papers  (2026-01-07T16:32:17Z)
• Improving Temporal Consistency and Fidelity at Inference-time in Perceptual Video Restoration by Zero-shot Image-based Diffusion Models [5.61537470581101]
  We address the challenge of improving temporal coherence in video restoration using zero-shot image-based diffusion models.<n>We propose two complementary inference-time strategies: Perceptual Straightening Guidance (PSG) and Ensemble Sampling (MPES)
  arXiv  Detail & Related papers  (2025-10-29T11:40:06Z)
• Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion [52.315729095824906]
  MLLM Semantic-Corrected Ping-Pong-Ahead Diffusion (PPAD) is a novel framework that introduces a Multimodal Large Language Model (MLLM) as a semantic observer during inference.<n>It performs real-time analysis on intermediate generations, identifies latent semantic inconsistencies, and translates feedback into controllable signals that actively guide the remaining denoising steps.<n>Extensive experiments demonstrate PPAD's significant improvements.
  arXiv  Detail & Related papers  (2025-05-26T14:42:35Z)
• Collaborative Feedback Discriminative Propagation for Video Super-Resolution [66.61201445650323]
  Key success of video super-resolution (VSR) methods stems mainly from exploring spatial and temporal information. Inaccurate alignment usually leads to aligned features with significant artifacts. propagation modules only propagate the same timestep features forward or backward.
  arXiv  Detail & Related papers  (2024-04-06T22:08:20Z)
• Intrinsic Temporal Regularization for High-resolution Human Video Synthesis [59.54483950973432]
  temporal consistency is crucial for extending image processing pipelines to the video domain. We propose an effective intrinsic temporal regularization scheme, where an intrinsic confidence map is estimated via the frame generator to regulate motion estimation. We apply our intrinsic temporal regulation to single-image generator, leading to a powerful " INTERnet" capable of generating $512times512$ resolution human action videos.
  arXiv  Detail & Related papers  (2020-12-11T05:29:45Z)

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.