Tesla autopilot mode was in use when a Model 3 crashed into a Texas home, killing 76-year-old Martha Avila, according to the driver and Harris County officials.

Instead of predicting discrete tokens, GPDiT autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics and semantic consistency across frames. This continuous autoregressive framework not only enhances generation quality but also endows the model with representation capabilities. Additionally, we introduce a lightweight causal attention variant and a parameter-free rotation-based time-conditioning mechanism, improving both the training and inference efficiency. Extensive experiments demonstrate that GPDiT achieves strong performance in video generation quality, video representation ability, and few-shot learning tasks, highlighting its potential as an effective framework for video modeling in continuous space.

We introduce TAPIP3D, a novel approach for long-term 3D point tracking in monocular RGB and RGB-D videos. TAPIP3D represents videos as camerastabilized spatio-temporal feature clouds, leveraging depth and camera motion information to lift 2D video features into a 3D world space where camera movement is effectively canceled out. Within this stabilized 3D representation, TAPIP3D iteratively refines multi-frame motion estimates, enabling robust point tracking over long time horizons.

Recent advances in Text-to-Image (T2I) diffusion models have transformed image generation, enabling significant progress in stylized generation using only a few style reference images. However, current diffusion-based methods struggle with fine-grained style customization due to challenges in controlling multiple style attributes, such as color and texture. This paper introduces the first tuning-free Target Contentapproach to achieve free-lunch color-texture disentanglement in stylized T2I generation,"A ligaddressinghthouse bthe needy tforhe sea"independently controlled style elements for the

One imagines Kane Parsons is less than pleased. Google is investing $75 million in the film studio A24 and the companies are teaming up to develop, wait for it, AI tools. Google says the partnership aims to expand what is possible in the future of entertainment. The multiyear deal doesn't give Google access to A24's library of film and television, so we won't have to suffer through a sloppified sequel to just yet. Instead, the companies will develop tools that assist with various aspects of filmmaking.

We introduce CameraBench, a large-scale dataset and benchmark designed to assess and improve camera motion understanding. CameraBench consists of 3,000 diverse internet videos, annotated by experts through a rigorous multi-stage quality control process. One of our core contributions is a taxonomy or "language" of camera motion primitives, designed in collaboration with cinematographers. We find, for example, that some primitives like "follow" (or tracking) require understanding scene content like moving subjects. We conduct a large-scale human study to quantify human annotation performance, revealing that domain expertise and tutorial-based training can significantly enhance accuracy. For example, a novice may confuse zoom-in(a change of intrinsics) with translating forward (a change of extrinsics), but can be trained to differentiate the two. Using CameraBench, we evaluate Structure-from-Motion (SfM) and Video-Language Models (VLMs), finding that SfM models struggle to capture semantic primitives that depend on scene content, while VLMs struggle to capture geometric primitives that require precise estimation of trajectories. We then fine-tune a generative VLM on CameraBench to achieve the best of both worlds and showcase its applications, including motion-augmented captioning, video question answering, and video-text retrieval. We hope our taxonomy, benchmark, and tutorials will drive future efforts towards the ultimate goal of understanding camera motions in any video.

We introduce CameraBench, a large-scale dataset and benchmark designed to assess and improve camera motion understanding. CameraBench consists of 3,000 diverse internet videos, annotated by experts through a rigorous multi-stage quality control process. One of our core contributions is a taxonomy or "language" of camera motion primitives, designed in collaboration with cinematographers. We find, for example, that some primitives like "follow" (or tracking) require understanding scene content like moving subjects. We conduct a large-scale human study to quantify human annotation performance, revealing that domain expertise and tutorial-based training can significantly enhance accuracy. For example, a novice may confuse zoom-in(a change of intrinsics) with translating forward (a change of extrinsics), but can be trained to differentiate the two. Using CameraBench, we evaluate Structure-from-Motion (SfM) and Video-Language Models (VLMs), finding that SfM models struggle to capture semantic primitives that depend on scene content, while VLMs struggle to capture geometric primitives that require precise estimation of trajectories. We then fine-tune a generative VLM on CameraBench to achieve the best of both worlds and showcase its applications, including motion-augmented captioning, video question answering, and video-text retrieval. We hope our taxonomy, benchmark, and tutorials will drive future efforts towards the ultimate goal of understanding camera motions in any video.

Controllable image generation has attracted increasing attention in recent years, enabling users to manipulate visual content such as identity and style. However, achieving simultaneous control over the 9D poses (location, size, and orientation) of multiple objects remains an open challenge. Despite recent progress, existing methods often suffer from limited controllability and degraded quality, falling short of comprehensive multi-object 9D pose control. To address these limitations, we propose SceneDesigner, a method for accurate and flexible multi-object 9-DoF pose manipulation. SceneDesigner incorporates a branched network to the pre-trained base model and leverages a new representation, CNOCS map, which encodes 9D pose information from the camera view.

Justices Samuel Alito and Clarence Thomas dissented from the Supreme Court's refusal to hear a case they say forces police to create separate rules based on race.

Latent Diffusion-based Text-to-Image (T2I) is a free image editing tool that typically reverses an image into noise, reconstructs it using its original text prompt, and then generates an edited version under a new target prompt. To preserve unaltered image content, features from the reconstruction are directly injected to replace selected features in the generation. However, this direct replacement often leads to feature incompatibility, compromising editing fidelity and limiting creative flexibility, particularly for non-rigid edits (e.g., structural or pose changes). In this paper, we aim to address these limitations by proposing FSI-Edit, a novel framework using frequency-and stochasticity-based feature injection for flexible image editing. First, FSI-Edit enhances feature consistency by injecting high-frequency components of reconstruction features into generation features, mitigating incompatibility while preserving the editing ability for major structures encoded in low-frequency information. Second, it introduces controlled noise into the replaced reconstruction features, expanding the generative space to enable diverse non-rigid edits beyond the original image's constraints. Experiments on non-rigid edits, e.g., addition, deletion, and pose manipulation, demonstrate that FSI-Edit outperforms existing baselines in target alignment, semantic fidelity and visual quality. Our work highlights the critical roles of frequency-aware design and stochasticity in overcoming rigidity in diffusion-based editing.