相关论文: Omni-Effects: Unified and Spatially-Controllable V…

Storytelling in real-world videos often unfolds through multiple shots -- discontinuous yet semantically connected clips that together convey a coherent narrative. However, existing multi-shot video generation (MSV) methods struggle to…

Unified multimodal models integrating visual understanding and generation face a fundamental challenge: visual generation incurs substantially higher computational costs than understanding, particularly for video. This imbalance motivates…

Reinforcement learning (RL) has emerged as a critical paradigm for post-training Vision-Language-Action (VLA) models, enabling embodied agents to adapt and improve through environmental interaction. However, existing RL frameworks for VLAs…

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…

While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a significant gap remains between their pretraining performance and real-world deployment…

Text-to-image diffusion models have recently taken center stage as pivotal tools in promoting visual creativity across an array of domains such as comic book artistry, children's literature, game development, and web design. These models…

Generating VectorArt from text prompts is a challenging vision task, requiring diverse yet realistic depictions of the seen as well as unseen entities. However, existing research has been mostly limited to the generation of single objects,…

Computer vision is increasingly effective at segmenting objects in images and videos; however, scene effects related to the objects -- shadows, reflections, generated smoke, etc -- are typically overlooked. Identifying such scene effects…

In robotics, Vision-Language-Action (VLA) models that integrate diverse multimodal signals from multi-view inputs have emerged as an effective approach. However, most prior work adopts static fusion that processes all visual inputs…

Recent Vision-Language Models (VLMs) \textit{e.g.} CLIP have made great progress in video recognition. Despite the improvement brought by the strong visual backbone in extracting spatial features, CLIP still falls short in capturing and…

In this paper, we introduce OneReward, a unified reinforcement learning framework that enhances the model's generative capabilities across multiple tasks under different evaluation criteria using only \textit{One Reward} model. By employing…

We propose a novel unsupervised method to autoregressively generate videos from a single frame and a sparse motion input. Our trained model can generate unseen realistic object-to-object interactions. Although our model has never been given…

Large Vision-Language Models (LVLMs) have achieved remarkable success in a wide range of multimodal tasks by integrating pre-trained vision encoders and large language models. However, current LVLMs primarily rely on visual features…

The spatio-temporal complexity of video data presents significant challenges in tasks such as compression, generation, and inpainting. We present four key contributions to address the challenges of spatiotemporal video processing. First, we…

Video object insertion is a critical task for dynamically inserting new objects into existing environments. Previous video generation methods focus primarily on synthesizing entire scenes while struggling with ensuring consistent object…

Recent advances in Vision-Language-Action (VLA) and world-model methods have improved generalization in tasks such as robotic manipulation and object interaction. However, Successful execution of such tasks depends on large, costly…

World models based on video generation demonstrate remarkable potential for simulating interactive environments but face persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and…

We introduce and define a novel task-Scene-Aware Visually-Driven Speech Synthesis, aimed at addressing the limitations of existing speech generation models in creating immersive auditory experiences that align with the real physical world.…

The landscape of publicly available vision foundation models (VFMs), such as CLIP and Segment Anything Model (SAM), is expanding rapidly. VFMs are endowed with distinct capabilities stemming from their pre-training objectives. For instance,…

Vision-language tasks, such as VQA, SNLI-VE, and VCR are challenging because they require the model's reasoning ability to understand the semantics of the visual world and natural language. Supervised methods working for vision-language…