Related papers: Skeleton2Stage: Reward-Guided Fine-Tuning for Phys…
Recent GRPO-based approaches built on flow matching models have shown remarkable improvements in human preference alignment for text-to-image generation. Nevertheless, they still suffer from the sparse reward problem: the terminal reward of…
We propose a gradient preconditioning method that makes reward-guided generation with one-step generative models both efficient and reliable. Test-time noise optimization can unlock substantially better reward-guided generations from…
Single-view 3D human reconstruction has achieved remarkable progress through the adoption of multi-view diffusion models, yet the recovered 3D humans often exhibit unnatural poses. This phenomenon becomes pronounced when reconstructing 3D…
In this work, we present DreamDance, a novel method for animating human images using only skeleton pose sequences as conditional inputs. Existing approaches struggle with generating coherent, high-quality content in an efficient and…
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…
Multi-legged robots offer enhanced stability in complex terrains, yet autonomously learning natural and robust motions in such environments remains challenging. Drawing inspiration from animals' progressive learning patterns, from simple to…
Generating realistic and structurally plausible human images into existing scenes remains a significant challenge for current generative models, which often produce artifacts like distorted limbs and unnatural poses. We attribute this…
Despite substantial progress in text-driven 3D human motion synthesis, generating realistic multi-person interaction sequences remains challenging. Notably, body inter-penetration is a pervasive issue from both data acquisition to the…
Humanoid Reaction Synthesis is pivotal for creating highly interactive and empathetic robots that can seamlessly integrate into human environments, enhancing the way we live, work, and communicate. However, it is difficult to learn the…
In this paper, we define and study a new Cloth2Body problem which has a goal of generating 3D human body meshes from a 2D clothing image. Unlike the existing human mesh recovery problem, Cloth2Body needs to address new and emerging…
Dance is an important human art form, but creating new dances can be difficult and time-consuming. In this work, we introduce Editable Dance GEneration (EDGE), a state-of-the-art method for editable dance generation that is capable of…
Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models. However, due to the lack of focus in feedback content, especially regarding the object type and quantity,…
Diffusion models have demonstrated strong generative capabilities across scientific domains, but often produce outputs that violate physical laws. We propose a new perspective by framing physics-informed generation as a sparse reward…
Adaptive recovery from fall incidents are essential skills for the practical deployment of wheeled-legged robots, which uniquely combine the agility of legs with the speed of wheels for rapid recovery. However, traditional methods relying…
Video-based gait analysis has become a promising approach for assessing motor impairment in children with cerebral palsy (CP). However, existing methods usually rely on either pose sequences or handcrafted gait features alone, making it…
Can humans identify AI-generated (fake) videos and provide grounded reasons? While video generation models have advanced rapidly, a critical dimension -- whether humans can detect deepfake traces within a generated video, i.e.,…
Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a…
Skinning and rigging are fundamental components in animation, articulated object reconstruction, motion transfer, and 4D generation. Existing approaches predominantly rely on Linear Blend Skinning (LBS), due to its simplicity and…
Recent advances in diffusion-based and autoregressive video generation models have achieved remarkable visual realism. However, these models typically lack accurate physical alignment, failing to replicate real-world dynamics in object…
Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we…