Related papers: VERTIGO: Visual Preference Optimization for Cinema…

While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures…

Vision generation remains a challenging frontier in artificial intelligence, requiring seamless integration of visual understanding and generative capabilities. In this paper, we propose a novel framework, Vision-Driven Prompt Optimization…

Generative AI has significantly changed industries by enabling text-driven image generation, yet challenges remain in achieving high-resolution outputs that align with fine-grained user preferences. Consequently, multi-round interactions…

Different users find different images generated for the same prompt desirable. This gives rise to personalized image generation which involves creating images aligned with an individual's visual preference. Current generative models are,…

Designing effective camera trajectories in virtual 3D environments is a challenging task even for experienced animators. Despite an elaborate film grammar, forged through years of experience, that enables the specification of camera motions…

We present VINO, a unified visual generator that performs image and video generation and editing within a single framework. Instead of relying on task-specific models or independent modules for each modality, VINO uses a shared diffusion…

We introduce ScenarioControl, the first vision-language control mechanism for learned driving scenario generation. Given a text prompt or an input image, Scenario-Control synthesizes diverse, realistic 3D scenario rollouts - including map,…

Generating realistic robotic manipulation videos is an important step toward unifying perception, planning, and action in embodied agents. While existing video diffusion models require large domain-specific datasets and struggle to…

Humans learn powerful representations of objects and scenes by observing how they evolve over time. Yet, outside of specific tasks that require explicit temporal understanding, static image pretraining remains the dominant paradigm for…

Video generative models have recently achieved notable advancements in synthesis quality. However, generating complex motions remains a critical challenge, as existing models often struggle to produce natural, smooth, and contextually…

Direct Preference Optimization (DPO) trains a language model using human preference data, bypassing the explicit reward modeling phase of Reinforcement Learning from Human Feedback (RLHF). By iterating over sentence pairs in a preference…

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO take into account the fact that learning certain…

The notable gap between user-provided and model-preferred prompts poses a significant challenge for generating high-quality images with text-to-image models, compelling the need for prompt engineering. Current studies on prompt engineering…

Many safety-critical applications, especially in autonomous driving, require reliable object detectors. They can be very effectively assisted by a method to search for and identify potential failures and systematic errors before these…

Text-to-3D generation automates 3D content creation from textual descriptions, which offers transformative potential across various fields. However, existing methods often struggle to align generated content with human preferences, limiting…

Controllability, temporal coherence, and detail synthesis remain the most critical challenges in video generation. In this paper, we focus on a commonly used yet underexplored cinematic technique known as Frame In and Frame Out.…

Imitation learning-based visuomotor policies excel at manipulation tasks but often produce suboptimal action trajectories compared to model-based methods. Directly mapping camera data to actions via neural networks can result in jerky…

Perceptual video compression adopts generative video modeling to improve perceptual realism but frequently sacrifices signal fidelity, diverging from the goal of video compression to faithfully reproduce visual signal. To alleviate the…

The narrative quality of a video fundamentally determines its perceptual value. Although existing video generation methods can produce visually appealing content, they predominantly rely on sparse conditioning signals such as text prompts…

Direct Preference Optimization (DPO) helps reduce hallucinations in Video Multimodal Large Language Models (VLLMs), but its reliance on offline preference data limits adaptability and fails to capture true video-response misalignment. We…