Related papers: Geometry-Guided Reinforcement Learning for Multi-v…

We present UniRef-Image-Edit, a high-performance multi-modal generation system that unifies single-image editing and multi-image composition within a single framework. Existing diffusion-based editing methods often struggle to maintain…

Masked Generative Models (MGM)s demonstrate strong capabilities in generating high-fidelity images. However, they need many sampling steps to create high-quality generations, resulting in slow inference speed. In this work, we propose…

3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…

Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generation models, which uses reward functions to enhance generation quality and human preference…

Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw video data often fail to capture meaningful geometric-aware structure in their learned…

While reinforcement learning (RL) over chains of thought has significantly advanced language models in tasks such as mathematics and coding, visual reasoning introduces added complexity by requiring models to direct visual attention,…

Text-to-3D form plays a crucial role in creating editable 3D scenes for AR/VR. Recent advances have shown promise in merging neural radiance fields (NeRFs) with pre-trained diffusion models for text-to-3D object generation. However, one…

Transferring appearance to 3D assets using different representations of the appearance object - such as images or text - has garnered interest due to its wide range of applications in industries like gaming, augmented reality, and digital…

Representing 3D scenes from multiview images is a core challenge in computer vision and graphics, which requires both precise rendering and accurate reconstruction. Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention…

The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient, high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based 2D editing models are harnessed to modify multi-view…

Robot assembly discovery is a challenging problem that lives at the intersection of resource allocation and motion planning. The goal is to combine a predefined set of objects to form something new while considering task execution with the…

View transformation robustness (VTR) is critical for deep-learning-based multi-view 3D object reconstruction models, which indicates the methods' stability under inputs with various view transformations. However, existing research seldom…

With recent advances, Feed-forward Reconstruction Models (FFRMs) have demonstrated great potential in reconstruction quality and adaptiveness to multiple downstream tasks. However, the excessive reliance on multi-view geometric annotations,…

Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with verifiable rewards (RLVR), which leverages automatically…

The application of rule-based reinforcement learning (RL) to multimodal large language models (MLLMs) introduces unique challenges and potential deviations from findings in text-only domains, particularly for perception-heavy tasks. This…

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

Despite the recent success of multi-view diffusion models for text/image-based 3D asset generation, instruction-based editing of 3D assets lacks surprisingly far behind the quality of generation models. The main reason is that recent…

Reconstructing real-world objects from multi-view images is essential for applications in 3D editing, AR/VR, and digital content creation. Existing methods typically prioritize either geometric accuracy (Multi-View Stereo) or photorealistic…

While few-step generative models have enabled powerful image and video generation at significantly lower cost, generic reinforcement learning (RL) paradigms for few-step models remain an unsolved problem. Existing RL approaches for few-step…

We study reinforcement learning (RL) problems in which agents observe the reward or transition realizations at their current state before deciding which action to take. Such observations are available in many applications, including…