CausalAlign is a new framework for diffusion‑based video generation models that tackles the problem of drifting camera ego‑motion over long horizons. It first diagnoses how ego‑motion is represented and changes during denoising, revealing a rise‑and‑fall pattern. Then it strengthens ego‑motion by aligning internal representations to a 3D foundation model in a delta‑token space that captures inter‑frame changes, improving motion accuracy, geometric consistency, and temporal smoothness while preserving visual quality.
arXiv:2511.18991v2 Announce Type: replace Abstract: Camera-controlled video generation has attracted increasing interest for its applications in simulation, gaming, and world modeling. However, curre...
WorldForge V2 introduces a training‑free guidance framework that refines video diffusion outputs along a target camera path using warped references and optical‑flow‑identified latent channels for selective guidance. It employs a dual‑path strategy to correct artifacts, a v‑cache to reduce refinement cost, and Trajectory LoRA adapters trained in two stages to focus on trajectory‑responsive network blocks. The approach achieves state‑of‑the‑art generation quality and trajectory accuracy with minimal training data, enabling reliable camera control across unseen scenes.
The paper introduces Driving with DINO (DwD), a framework that uses Vision Foundation Module (VFM) features to bridge simulation and real-world domains for autonomous driving video generation. It addresses the consistency‑realism dilemma by projecting VFM features onto a principal subspace, dropping high‑frequency texture elements, and applying a Random Channel Tail Drop to preserve structural detail. Additional components— a learnable Spatial Alignment Module and a Causal Temporal Aggregator— enhance control precision, spatial alignment, and temporal stability, reducing motion blur and ensuring realistic, consistent outputs.
Momentum introduces a two-stage pipeline for video world models that uses synchronized multi-camera rigs to represent evolving scenes. The WorldUpdate stage generates shared reference-camera videos as a memory of scene dynamics, while WorldInteract grounds target camera video generation in this memory, ensuring moving objects remain represented outside the field of view. Experiments on CARLA street scenes show a 126.2% improvement in dynamic scene consistency over static image conditioning.
arXiv:2608. 19556v1 Announce Type: cross Abstract: Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion.
arXiv:2606. 19676v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation and editing.
World in World introduces a training‑free, inference‑time interface that transforms diverse control signals—such as source‑video observations, target‑view projections, geometry renderings, and retrieved states—into camera‑ and time‑labelled visual states. These states are processed by a frozen causal video model’s self‑attention, enabling tasks like camera‑controlled rerendering, long‑horizon revisiting, and human‑motion transfer without additional training. The method employs a correspondence router and evidence‑wise attention to align token identities and regulate auxiliary channel contributions during a single denoising pass.
WorldAlign introduces a decoupled 4D reward framework for improving world consistency in generated videos. It separates static regions from dynamic subjects, aligning each with a suitable world prior—geometric priors for static geometry and a vision‑language model for dynamic subjects—using masked reprojection and a VLM‑as‑a‑judge reward. The method enhances both static and dynamic consistency in pretrained image‑to‑video generators without relying on human preference data.
PoseRegen is a new framework for removing video watermarks while maintaining temporal consistency and motion fidelity. It first applies a shared viewpoint transformation to break watermark patterns, then reconstructs the sequence with a pose‑conditioned video model and Flow Matching supervision to preserve identity and background. The method also includes a Pose‑Conditioned Motion Consistency Adapter to keep body‑part trajectories stable, achieving near‑random watermark bit accuracy and outperforming baselines on motion metrics.
arXiv:2607. 27036v1 Announce Type: cross Abstract: Video diffusion-based world models enable long autoregressive video generation for robotics, autonomous driving and simulation tasks, yet sliding-window autoregressive inference suffers from severe error accumulation that degrades frame quality over time.
LiveVVT introduces a rolling streaming diffusion framework for video virtual try‑on that maintains high visual fidelity while enabling real‑time performance. It preserves bounded bidirectional modeling within a fixed‑size window, emits clean video chunks iteratively, and uses two memory modules—a bounded temporal memory and a persistent global appearance memory—to sustain long‑term consistency. A progressive distillation process further aligns teacher‑based bidirectional learning with causal few‑step inference, resulting in superior generation quality with 26× lower latency and 11× higher throughput compared to comparable models.
The paper introduces Relax Forcing, a training‑free memory mechanism for autoregressive video diffusion that structures temporal context into Sink, Tail, and History frames. By selecting History frames with a relaxation criterion, the method reduces error accumulation and attention overhead while preserving motion dynamics. Experiments on VBench‑Long demonstrate that this structured memory improves long‑video generation quality over existing baselines.