Related papers: PhysMoDPO: Physically-Plausible Humanoid Motion wi…
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…
Diffusion models demonstrate superior performance in capturing complex distributions from large-scale datasets, providing a promising solution for quadrupedal locomotion control. However, the robustness of the diffusion planner is…
Humanoid loco-manipulation requires coordinated high-level motion plans with stable, low-level whole-body execution under complex robot-environment dynamics and long-horizon tasks. While diffusion policies (DPs) show promise for learning…
With the rapid development of AIGC technology, significant progress has been made in diffusion model-based technologies for text-to-image (T2I) and text-to-video (T2V). In recent years, a few studies have introduced the strategy of Direct…
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…
We introduce DreamControl, a novel methodology for learning autonomous whole-body humanoid skills. DreamControl leverages the strengths of diffusion models and Reinforcement Learning (RL): our core innovation is the use of a diffusion prior…
Dynamic loco-manipulation calls for effective whole-body control and contact-rich interactions with the object and the environment. Existing learning-based control synthesis relies on training low-level skill policies and explicitly…
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…
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…
Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization (DPO) for these models and identify a critical pathology:…
Imitation learning from human demonstrations enables robots to perform complex manipulation tasks and has recently witnessed huge success. However, these techniques often struggle to adapt behavior to new preferences or changes in the…
Recent studies have shown the great potential of diffusion models in improving reinforcement learning (RL) by modeling complex policies, expressing a high degree of multi-modality, and efficiently handling high-dimensional continuous…
Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviate from user…
Direct Preference Optimization (DPO) has recently been applied as a post-training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from…
Recent advancements in human preference optimization, initially developed for Language Models (LMs), have shown promise for text-to-image Diffusion Models, enhancing prompt alignment, visual appeal, and user preference. Unlike LMs,…
Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) generative models is still relatively uncharted territory.…
Humanoid robots are machines built with an anthropomorphic shape. Despite decades of research into the subject, it is still challenging to tackle the robot locomotion problem from an algorithmic point of view. For example, these machines…
Generating highly dynamic and photorealistic portrait animations driven by audio and skeletal motion remains challenging due to the need for precise lip synchronization, natural facial expressions, and high-fidelity body motion dynamics. We…
Direct preference optimization (DPO) methods have shown strong potential in aligning text-to-image diffusion models with human preferences by training on paired comparisons. These methods improve training stability by avoiding the REINFORCE…
The practical applications of diffusion models have been limited by the misalignment between generated images and corresponding text prompts. Recent studies have introduced direct preference optimization (DPO) to enhance the alignment of…