ICLR 2026 论文列表

Controllable video generation (CVG) has advanced rapidly, yet current systems falter when more than one actor must move, interact, and exchange positions under noisy control signals. We address this gap with DanceTogether, the first end-to-end diffusion framework that turns a single reference image plus independent pose-mask streams into long, photorealistic videos while strictly preserving every identity. A novel MaskPoseAdapter binds “who” and “how” at every denoising step by fusing robust tracking masks with semantically rich but noisy pose heat maps, eliminating the identity drift and appearance bleeding that plague frame-wise pipelines. To train and evaluate at scale, we introduce (i) PairFS-4K, 26 h of dual-skater footage with more than 7 000 distinct IDs, (ii) HumanRob-300, a one-hour humanoid-robot interaction set for rapid cross-domain transfer, and (iii) TogetherVideoBench, a three-track benchmark centred on the DanceTogEval-100 test suite covering dance, boxing, wrestling, yoga, and figure skating. On TogetherVideoBench, DanceTogether outperforms the prior arts by a significant margin. Moreover, we show that a one-hour fine-tune yields convincing human-robot videos, underscoring broad generalisation to embodied-AI and HRI tasks. Extensive ablations confirm that persistent identity-action binding is critical to these gains. Together, our model, datasets, and benchmark lift CVG from single-subject choreography to compositionally controllable, multi-actor interaction, opening new avenues for digital production, simulation, and embodied intelligence.

Textual Inversion (TI) is an efficient approach to text‑to‑image personalization but often fails on complex prompts. We trace these failures to embedding norm inflation: learned tokens drift to out‑of‑distribution magnitudes, degrading prompt conditioning in pre‑norm Transformers. Empirically, we show semantics are primarily encoded by direction in CLIP token space, while inflated norms harm contextualization; theoretically, we analyze how large magnitudes attenuate positional information and hinder residual updates in pre‑norm blocks. We propose Directional Textual Inversion (DTI), which fixes the embedding magnitude to an in‑distribution scale and optimizes only direction on the unit hypersphere via Riemannian SGD. We cast direction learning as MAP with a von Mises–Fisher prior, yielding a constant‑direction prior gradient that is simple and efficient to incorporate. Across personalization tasks, DTI improves text fidelity over TI and TI‑variants while maintaining subject similarity. Crucially, DTI’s hyperspherical parameterization enables smooth, semantically coherent interpolation between learned concepts (slerp), a capability that is absent in standard TI. Our findings suggest that direction‑only optimization is a robust and scalable path for prompt‑faithful personalization.

Diffusion transformers typically incorporate textual information via (i) attention layers and (ii) a modulation mechanism using a pooled text embedding. Nevertheless, recent approaches discard modulation-based text conditioning and rely exclusively on attention. In this paper, we address whether modulation-based text conditioning is necessary and whether it can provide any performance advantage. Our analysis shows that, in its conventional usage, the pooled embedding contributes little to overall performance, suggesting that attention alone is generally sufficient for faithfully propagating prompt information. However, we reveal that the pooled embedding can provide significant gains when used from a different perspective—serving as guidance and enabling controllable shifts toward more desirable properties. This approach is training-free, simple to implement, incurs negligible runtime overhead, and can be applied to various diffusion models, bringing improvements across diverse tasks, including text-to-image/video generation and image editing.

Recent diffusion models have achieved remarkable success in image relighting, and this success has quickly been reproduced in video relighting. Although these methods can relight videos under various conditions, their ability to explicitly control the illumination in the relighted video remains limited. Therefore, we present LightCtrl, the first controllable video relighting method that offers explicit control over the video illumination through a user-supplied light trajectory in a training-free manner. This is essentially achieved by leveraging a hybrid approach that combines pre-trained diffusion models: a pre-trained image relighting diffusion model is used to relight each frame individually, followed by a video diffusion prior that enhances the temporal consistency of the relighted sequence. In particular, to enable explicit control over dynamically varying lighting in the relighted video, we introduce two key components. First, the Light Map Injection module samples light trajectory-specific noise and injects it into the latent representation of the source video, significantly enhancing illumination coherence with respect to the conditional light trajectory. Second, the Geometry-Aware Relighting module dynamically combines RGB and normal map latents in the frequency domain to suppress the influence of the original lighting in the input video, thereby further improving the relighted video's adherence to the input light trajectory. Our experiments demonstrate that LightCtrl can generate high-quality video results with diverse illumination changes closely following the light trajectory condition, indicating improved controllability over baseline methods. The code will be released to facilitate future studies.

Recent advancements in Diffusion Transformers (DiTs) have established them as the state-of-the-art method for video generation. However, their inherently sequential denoising process results in inevitable latency, limiting real-world applicability. Existing acceleration methods either compromise visual quality due to architectural modifications or fail to reuse intermediate features at proper granularity. Our analysis reveals that DiT blocks are the primary contributors to inference latency. Across diffusion timesteps, the feature variations of DiT blocks exhibit a U-shaped pattern with high similarity during intermediate timesteps, which suggests substantial computational redundancy. In this paper, we propose Block-Wise Caching (BWCache), a training-free method to accelerate DiT-based video generation. BWCache dynamically caches and reuses features from DiT blocks across diffusion timesteps. Furthermore, we introduce a similarity indicator that triggers feature reuse only when the differences between block features at adjacent timesteps fall below a threshold, thereby minimizing redundant computations while maintaining visual fidelity. Extensive experiments on several video diffusion models demonstrate that BWCache achieves up to 2.24$\times$ speedup with comparable visual quality.

The rapid advancement of video diffusion models has been hindered by fundamental limitations in temporal modeling, particularly the rigid synchronization of frame evolution imposed by conventional scalar timestep variables. While task-specific adaptations and autoregressive models have sought to address these challenges, they remain constrained by computational inefficiency, catastrophic forgetting, or narrow applicability. In this work, we present \textbf{Pusa} V1.0, a versatile model that leverages \textbf{vectorized timestep adaptation (VTA)} to enable fine-grained temporal control within a unified video diffusion framework. Note that VTA is a non-destructive adaptation, which means that it fully preserves the capabilities of the base model. \textbf{Unlike conventional methods like Wan-I2V, which finetune a base text-to-video (T2V) model with abundant resources to do image-to-video (I2V), we achieve comparable results in a zero-shot manner after an ultra-efficient finetuning process based on VTA. Moreover, this method also unlocks many other zero-shot capabilities simultaneously, such as start-end frames and video extension ---all without task-specific training. Meanwhile, it keeps the T2V capability from the base model.} Mechanistic analyses also reveal that our approach preserves the foundation model's generative priors while surgically injecting temporal dynamics, avoiding the combinatorial explosion inherent to the vectorized timestep. This work establishes a scalable, efficient, and versatile paradigm for next-generation video synthesis, democratizing high-fidelity video generation for research and industry alike.

Real-time motion-controllable video generation remains challenging due to the inherent latency of bidirectional diffusion models and the lack of effective autoregressive (AR) approaches. Existing AR video diffusion models are limited to simple control signals or text-to-video generation, and often suffer from quality degradation and motion artifacts in few-step generation. To address these challenges, we propose AR-Drag, the first RL-enhanced few-step AR video diffusion model for real-time image-to-video generation with diverse motion control. We first fine-tune a base I2V model to support basic motion control, then further improve it via reinforcement learning with a trajectory-based reward model. Our design preserves the Markov property through a Self-Rollout mechanism and accelerates training by selectively introducing stochasticity in denoising steps. Extensive experiments demonstrate that AR-Drag achieves high visual fidelity and precise motion alignment, significantly reducing latency compared with state-of-the-art motion-controllable VDMs, while using only 1.3B parameters. Codes are available in Supplementary Materials.

We present a target-aware video diffusion model that generates videos from an input image, in which an actor interacts with a specified target while performing a desired action. The target is defined by a segmentation mask, and the action is described through a text prompt. Our key motivation is to incorporate target awareness into video generation, enabling actors to perform directed actions on designated objects. This enables video diffusion models to act as motion planners, producing plausible predictions of human–object interactions by leveraging the priors of large-scale video generative models. We build our target-aware model by extending a baseline model to incorporate the target mask as an additional input. To enforce target awareness, we introduce a special token that encodes the target's spatial information within the text prompt. We then fine-tune the model with our curated dataset using an additional cross-attention loss that aligns the cross-attention maps associated with this token with the input target mask. To further improve performance, we selectively apply this loss to the most semantically relevant attention regions and transformer blocks. Experimental results show that our target-aware model outperforms existing solutions in generating videos where actors interact accurately with the specified targets. We further demonstrate its efficacy in two downstream applications: zero-shot 3D HOI motion synthesis with physical plausibility and long-term video content creation.

Traditional cartoon and anime production involves keyframing, inbetweening, and colorization stages, which require intensive manual effort. Despite recent advances in AI, existing methods often handle these stages separately, leading to error accumulation and artifacts. For instance, inbetweening approaches struggle with large motions, while colorization methods require dense per-frame sketches. To address this, we introduce ToonComposer, a generative model that unifies inbetweening and colorization into a single post-keyframing stage. ToonComposer employs a sparse sketch injection mechanism to provide precise control using keyframe sketches. Additionally, we propose a novel cartoon adaptation method with the spatial low-rank adapter (SLRA) to effectively tailor a modern video foundation model to the cartoon domain while keeping its temporal prior intact. Requiring as few as a single sketch and a colored reference frame, ToonComposer excels with sparse inputs, while also supporting multiple sketches at any temporal location for more precise motion control. This dual capability reduces manual workload and improves flexibility, empowering artists in real-world scenarios. To evaluate our model, we further created PKBench, a benchmark featuring human-drawn sketches that simulate real-world use cases. Our evaluation demonstrates that ToonComposer outperforms existing methods in visual quality, motion consistency, and production efficiency, offering a superior and more flexible solution for AI-assisted cartoon production.

Diffusion Transformer models have driven the rapid advances in video generation, achieving state-of-the-art quality and flexibility. However, their attention mechanism remains a major performance bottleneck, as its dense computation scales quadratically with the sequence length. To overcome this limitation and reduce the generation latency, we propose DSA, a novel attention mechanism that integrates sparse attention with distributed inference for diffusion-based video generation. By leveraging carefully-designed parallelism strategies and scheduling, DSA significantly reduces redundant computation while preserving global context. Extensive experiments on benchmark datasets demonstrate that, when deployed on 8 GPUs, DSA achieves up to 1.43× inference speedup than the existing distributed method and 10.79× faster than single-GPU inference.

Understanding and predicting dynamics of the physical world can enhance a robot's ability to plan and interact effectively in complex environments. While recent video generation models have shown strong potential in modeling dynamic scenes, generating videos that are both temporally coherent and geometrically consistent across camera views remains a significant challenge. To address this, we propose a 4D video generation model that enforces multi-view 3D consistency of generated videos by supervising the model with cross-view pointmap alignment during training. Through this geometric supervision, the model learns a shared 3D scene representation, enabling it to generate spatio-temporally aligned future video sequences from novel viewpoints given a single RGB-D image per view, and without relying on camera poses as input. Compared to existing baselines, our method produces more visually stable and spatially aligned predictions across multiple simulated and real-world robotic datasets. We further show that the predicted 4D videos can be used to recover robot end-effector trajectories using an off-the-shelf 6DoF pose tracker, yielding robot manipulation policies that generalize well to novel camera viewpoints.

The choice of initial noise strongly affects quality and prompt alignment in video diffusion; different seeds for the same prompt can yield drastically different results. While recent methods use externally designed priors (e.g., frequency filtering or inter-frame smoothing), they often overlook internal model signals that indicate inherently preferable seeds. To address this, we propose ANSE (Active Noise Selection for Generation), a model-aware framework that selects high-quality seeds by quantifying attention-based uncertainty. At its core is BANSA (Bayesian Active Noise Selection via Attention), an acquisition function that measures entropy disagreement across multiple stochastic attention samples to estimate model confidence and consistency. For efficient inference-time deployment, we introduce a Bernoulli-masked approximation of BANSA that estimates scores from a single diffusion step and a subset of informative attention layers. Experiments across diverse text-to-video backbones demonstrate improved video quality and temporal coherence with marginal inference overhead, providing a principled and generalizable approach to noise selection in video diffusion.

Long video generation with Diffusion Transformers (DiTs) is bottlenecked by the quadratic scaling of full attention with sequence length. Since attention is highly redundant, outputs are dominated by a small subset of query–key pairs. Existing sparse methods rely on blockwise coarse estimation, whose accuracy–efficiency trade-offs are constrained by block size. This paper introduces Mixture-of-Groups Attention (MoGA), an efficient sparse attention that uses a lightweight, learnable token router to precisely match tokens without blockwise estimation. Through semantic-aware routing, MoGA enables effective long-range interactions. As a kernel-free method, MoGA integrates seamlessly with modern attention stacks, including FlashAttention and sequence parallelism. Building on MoGA, we develop an efficient long video generation model that end-to-end produces minute-level, multi-shot, 480p videos at 24 fps, with a context length of approximately 580k. Comprehensive experiments on various video generation tasks validate the effectiveness of our approach. We provide an anonymous link \url{https://anonymous.4open.science/r/MoGA} to showcase the generated videos.