Related papers: SAGE: Structure-Aware Generative Video Transitions…

Despite recent advances in retrieval-augmented generation (RAG) for video understanding, effectively understanding long-form video content remains underexplored due to the vast scale and high complexity of video data. Current RAG approaches…

In this paper, we propose VideoFrom3D, a novel framework for synthesizing high-quality 3D scene videos from coarse geometry, a camera trajectory, and a reference image. Our approach streamlines the 3D graphic design workflow, enabling…

We present a method for generating video sequences with coherent motion between a pair of input key frames. We adapt a pretrained large-scale image-to-video diffusion model (originally trained to generate videos moving forward in time from…

In the latest advancements in multimodal learning, effectively addressing the spatial and semantic losses of visual data after encoding remains a critical challenge. This is because the performance of large multimodal models is positively…

Large vision-language models, such as CLIP, have shown strong zero-shot classification performance by aligning images and text in a shared embedding space. However, CLIP models often develop multimodal spurious biases, which is the…

Training modern neural networks on large datasets is computationally and energy intensive. We present SAGE, a streaming data-subset selection method that maintains a compact Frequent Directions (FD) sketch of gradient geometry in $O(\ell…

Following the advent of NeRFs, 3D Gaussian Splatting (3D-GS) has paved the way to real-time neural rendering overcoming the computational burden of volumetric methods. Following the pioneering work of 3D-GS, several methods have attempted…

The rising popularity of immersive visual experiences has increased interest in stereoscopic 3D video generation. Despite significant advances in video synthesis, creating 3D videos remains challenging due to the relative scarcity of 3D…

Vision-centric autonomous driving systems rely on diverse and scalable training data to achieve robust performance. While video object editing offers a promising path for data augmentation, existing methods often struggle to maintain both…

Leveraging text, images, structure maps, or motion trajectories as conditional guidance, diffusion models have achieved great success in automated and high-quality video generation. However, generating smooth and rational transition videos…

Existing AI-driven video creation systems typically treat script drafting and key-shot design as two disjoint tasks: the former relies on large language models, while the latter depends on image generation models. We argue that these two…

Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited high-quality data and…

This work addresses the lack of multimodal generative models capable of producing high-quality videos with spatially aligned audio. While recent advancements in generative models have been successful in video generation, they often overlook…

Diffusion models manifest evident benefits across diverse domains, yet their high sampling cost, requiring dozens of sequential model evaluations, remains a major limitation. Prior efforts mainly accelerate sampling via optimized solvers or…

Although existing video editing methods are generally feasible, they often require many costly iterations and still struggle to deliver high-quality yet satisfying editing results. We attribute this limitation to the prevalent data-to-data…

With the explosive popularity of AI-generated content (AIGC), video generation has recently received a lot of attention. Generating videos guided by text instructions poses significant challenges, such as modeling the complex relationship…

Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…

Video generation has seen remarkable progress thanks to advancements in generative deep learning. However, generating long sequences remains a significant challenge. Generated videos should not only display coherent and continuous movement…

Systems analysis students increasingly use Generative AI, yet current pedagogy lacks systematic approaches for teaching responsible AI orchestration that fosters critical thinking whilst meeting educational outcomes. Students risk accepting…

Speculative decoding has emerged as a promising approach to accelerate inference in vision-language models (VLMs) by enabling parallel verification of multiple draft tokens. However, existing methods rely on static tree structures that…