Related papers: RLGF: Reinforcement Learning with Geometric Feedba…

Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm. However, maintaining multi-view consistency in edited results remains challenging, and the extreme scarcity of 3D-consistent editing paired…

Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Supervised Fine-Tuning using synthetic datasets. At present, there is an extreme…

Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts such as object deformation, spatial drift, and depth violations in generated videos. To address this limitation, we propose a…

Large vision-language models are steadily gaining personalization capabilities at the cost of fine-tuning or data augmentation. We present two models for image generation using model-agnostic learning that align semantic priors with…

Recent advances in video diffusion models have remarkably improved camera-controlled video generation, but most methods rely solely on supervised fine-tuning (SFT), leaving online reinforcement learning (RL) post-training largely…

Recent advances in video world modeling have enabled large-scale generative models to simulate embodied environments with high visual fidelity, providing strong priors for prediction, planning, and control. Yet, despite their realism, these…

Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying…

Generating physically realistic 3D molecular structures remains a core challenge in molecular generative modeling. While diffusion models equipped with equivariant neural networks have made progress in capturing molecular geometries, they…

Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-language models (VLMs) have enabled high-quality SVG generation by framing the problem as a code…

A single-pass driving clip frequently results in incomplete scanning of the road structure, making reconstructed scene expanding a critical requirement for sensor simulators to effectively regress driving actions. Although contemporary 3D…

Generating structured, editable diagrams remains a significant challenge for contemporary large language models, despite their proficiency in general-purpose vector code generation. The primary difficulty lies in the structural fragility of…

Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object deformation, texture drift, and non-rigid backgrounds under…

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…

Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitation in rendering rigid body motion, a core tenet of…

Existing Gaussian splatting methods often fall short in achieving satisfactory novel view synthesis in driving scenes, primarily due to the absence of crafty designs and geometric constraints for the involved elements. This paper introduces…

Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs) by aligning their outputs with desired human values through instruction tuning. However, RLHF…

\textbf{Synthetic human dynamics} aims to generate photorealistic videos of human subjects performing expressive, intention-driven motions. However, current approaches face two core challenges: (1) \emph{geometric inconsistency} and…

Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies…

Neural reconstruction models for autonomous driving simulation have made significant strides in recent years, with dynamic models becoming increasingly prevalent. However, these models are typically limited to handling in-domain objects…

Despite the promise of RLHF in aligning LLMs with human preferences, it often leads to superficial alignment, prioritizing stylistic changes over improving downstream performance of LLMs. Underspecified preferences could obscure directions…