Related papers: Reasoning Physical Video Generation with Diffusion…
Perceptual studies demonstrate that conditional diffusion models excel at reconstructing video content aligned with human visual perception. Building on this insight, we propose a video compression framework that leverages conditional…
Text-driven human motion generation in computer vision is both significant and challenging. However, current methods are limited to producing either deterministic or imprecise motion sequences, failing to effectively control the temporal…
Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but…
Generating high-quality and person-generic visual dubbing remains a challenge. Recent innovation has seen the advent of a two-stage paradigm, decoupling the rendering and lip synchronization process facilitated by intermediate…
Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion…
Vision-Language Models have excelled at textual reasoning, but they often struggle with fine-grained spatial understanding and continuous action planning, failing to simulate the dynamics required for complex visual reasoning. In this work,…
Visual tokenizers play a crucial role in diffusion models. The dimensionality of latent space governs both reconstruction fidelity and the semantic expressiveness of the latent feature. However, a fundamental trade-off is inherent between…
Text-to-video generation is an emerging field in generative AI, enabling the creation of realistic, semantically accurate videos from text prompts. While current models achieve impressive visual quality and alignment with input text, they…
We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified…
Video retrieval is a challenging research topic bridging the vision and language areas and has attracted broad attention in recent years. Previous works have been devoted to representing videos by directly encoding from frame-level…
Generating long-term, coherent, and realistic music-conditioned dance sequences remains a challenging task in human motion synthesis. Existing approaches exhibit critical limitations: motion graph methods rely on fixed template libraries,…
How to improve the ability of scene representation is a key issue in vision-oriented decision-making applications, and current approaches usually learn task-relevant state representations within visual reinforcement learning to address this…
Text-to-video models have recently undergone rapid and substantial advancements. Nevertheless, due to limitations in data and computational resources, achieving efficient generation of long videos with rich motion dynamics remains a…
Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i.e., p(candidates|query). While straightforward, this de facto paradigm overlooks the underlying data…
Music profoundly enhances video production by improving quality, engagement, and emotional resonance, sparking growing interest in video-to-music generation. Despite recent advances, existing approaches remain limited in specific scenarios…
Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories. While reinforcement learning with…
Recent diffusion-based text-to-image customization methods have achieved significant success in understanding concrete concepts to control generation processes, such as styles and shapes. However, few efforts dive into the realistic yet…
Large-scale pre-trained diffusion models have exhibited remarkable capabilities in diverse video generations. Given a set of video clips of the same motion concept, the task of Motion Customization is to adapt existing text-to-video…
Automated discovery of physical laws from observational data in the real world is a grand challenge in AI. Current methods, relying on symbolic regression or LLMs, are limited to uni-modal data and overlook the rich, visual phenomenological…
Reinforcement learning for training end-to-end autonomous driving models in closed-loop simulations is gaining growing attention. However, most simulation environments differ significantly from real-world conditions, creating a substantial…