Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories

• URL: http://arxiv.org/abs/2606.22527v1
• Date: Sun, 21 Jun 2026 14:25:50 GMT
• Title: Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories
• Abstract summary: Diffusion and flow-based generative models produce strong images, yet their controllability remains largely endpoint-centric.<n>Recent methods have begun to exploit generation order and process decomposition to improve sample quality, but still treat intermediate states as internal computation rather than objects for interaction.<n>We propose Trajectory Forcing (TF), a trajectory-centric framework that makes the generation path explicit, semantic, and editable.
• Score: 62.54876287800644
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion and flow-based generative models produce strong images, yet their controllability remains largely endpoint-centric: users specify conditions and receive final outputs, while the intermediate generative dynamics remain hidden. Recent methods have begun to exploit generation order and process decomposition to improve sample quality, but still treat intermediate states as internal computation rather than objects for interaction. We propose Trajectory Forcing (TF), a trajectory-centric framework that makes the generation path explicit, semantic, and editable. TF organizes synthesis as a sequence of semantically structured stages, progressing from global layout to object-, part-, and detail-level representations. Each stage produces a decodable latent state that can be inspected, evaluated, and locally edited before the next stage begins. To instantiate this path, we derive coarse-to-fine teacher hierarchies by clustering pretrained visual representations such as DINOv2, and train a hierarchy-conditioned one-step flow-matching model at each level. We further introduce trajectory-aware metrics that measure structural consistency and local controllability beyond endpoint quality metrics such as FID. Experiments show that TF achieves competitive sample quality while exposing coherent intermediate states and supporting localized edits across semantic levels. By shifting the focus from final images to the generative path itself, TF opens a route toward controllable, trajectory-aware image synthesis.

Related papers

• COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation [8.166232715151436]
  We propose a training-free framework that progressively optimize object-level features via the Field-of-View (FoV) expansion.<n>Our approach consistently outperforms state-of-the-art methods across semantic alignment, image quality, and spatial fidelity.
  arXiv  Detail & Related papers  (2026-05-31T02:10:34Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning [14.22776855572358]
  Scene-level point cloud self-supervised learning (PC-SSL) has demonstrated potential in enhancing the generalization capability of 3D vision models.<n>We propose a PC-SSL framework based on cross-sample semantic propagation (CSP), in which samples within a batch are serialized into continuous input and processed by a state-space model to enable semantic state propagation.<n>This mechanism explicitly models the dynamic dependencies across samples in the state space, allowing the network to establish cross-sample semantic consistency in the latent space and achieve global semantic alignment.
  arXiv  Detail & Related papers  (2026-05-03T07:40:00Z)
• Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning [59.262311672150055]
  We introduce process-driven image generation, a multi-step paradigm that decomposes synthesis into an interleaved reasoning trajectory.<n>A core challenge of process-driven generation stems from the ambiguity of intermediate states.<n>We address this through dense, step-wise supervision that maintains two complementary constraints.
  arXiv  Detail & Related papers  (2026-04-06T15:11:57Z)
• Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection [21.20482802952099]
  Open-Vocabulary Temporal Action Detection aims to classify and localize action segments in untrimmed videos for unseen categories.<n>Previous methods rely solely on global alignment between label-level semantics and visual features.<n>We propose a Phase-wise Decomposition and Alignment framework, which enables fine-grained action pattern learning.
  arXiv  Detail & Related papers  (2026-03-25T07:45:04Z)
• Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers [49.08465459791972]
  Region-instructed layout control in text-to-image generation is highly practical, yet existing methods suffer from limitations.<n>By modeling regional generation as distinct layers and binding them during the generation, we propose LayerBind.
  arXiv  Detail & Related papers  (2026-03-06T00:09:49Z)
• Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models [13.707653566827704]
  Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret.<n>Existing explainability methods rely on final-layer attributions, capture either local token-level attributions or global attention patterns without unification.<n>We propose a unified hierarchical attribution framework that computes layer-wise Integrated Gradients within each Transformer block and fuses these token-level attributions with class-specific attention gradients.
  arXiv  Detail & Related papers  (2026-02-18T17:03:10Z)
• HiCoGen: Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement Learning [66.99487505369254]
  HiCoGen is built upon a novel Chain of Synthesis paradigm.<n>It decomposes complex prompts into minimal semantic units.<n>It then synthesizes these units iteratively, where the image generated in each step provides crucial visual context for the next.<n>Experiments show our approach significantly outperforms existing methods in both concept coverage and compositional accuracy.
  arXiv  Detail & Related papers  (2025-11-25T06:24:25Z)
• GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning [55.79997930181418]
  Generalized Zero-Shot Learning aims to recognize images from both the seen and unseen classes by transferring semantic knowledge from seen to unseen classes. It is a promising solution to take the advantage of generative models to hallucinate realistic unseen samples based on the knowledge learned from the seen classes. We propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation.
  arXiv  Detail & Related papers  (2022-07-05T04:04:37Z)

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.