Heyuan Yao

Heyuan Yao, Zhenhua Song, Baoquan Chen et al.

In this paper, we introduce ControlVAE, a novel model-based framework for learning generative motion control policies based on variational autoencoders (VAE). Our framework can learn a rich and flexible latent representation of skills and a skill-conditioned generative control policy from a diverse set of unorganized motion sequences, which enables the generation of realistic human behaviors by sampling in the latent space and allows high-level control policies to reuse the learned skills to accomplish a variety of downstream tasks. In the training of ControlVAE, we employ a learnable world model to realize direct supervision of the latent space and the control policy. This world model effectively captures the unknown dynamics of the simulation system, enabling efficient model-based learning of high-level downstream tasks. We also learn a state-conditional prior distribution in the VAE-based generative control policy, which generates a skill embedding that outperforms the non-conditional priors in downstream tasks. We demonstrate the effectiveness of ControlVAE using a diverse set of tasks, which allows realistic and interactive control of the simulated characters.

Heyuan Yao, Zhenhua Song, Yuyang Zhou et al.

In this work, we present MoConVQ, a novel unified framework for physics-based motion control leveraging scalable discrete representations. Building upon vector quantized variational autoencoders (VQ-VAE) and model-based reinforcement learning, our approach effectively learns motion embeddings from a large, unstructured dataset spanning tens of hours of motion examples. The resultant motion representation not only captures diverse motion skills but also offers a robust and intuitive interface for various applications. We demonstrate the versatility of MoConVQ through several applications: universal tracking control from various motion sources, interactive character control with latent motion representations using supervised learning, physics-based motion generation from natural language descriptions using the GPT framework, and, most interestingly, seamless integration with large language models (LLMs) with in-context learning to tackle complex and abstract tasks.

Yusen Feng, Xiang Wang, Heyuan Yao et al.

This paper presents MuGen, a data-driven framework for learning and deploying multi-skill locomotion on humanoid robots. MuGen enables a robot to perform expressive motions like humans under the guidance of example motion sequences. To achieve this, we employ vector-quantized autoencoders (VQ-VAEs) trained with model-based reinforcement learning, resulting in a generative representation of locomotion that captures key patterns of human motion from hours of heterogeneous human performance data. We employ a teacher-student learning framework and develop a new policy distillation strategy to enable a deployable student policy learning this efficient latent representation. This policy allows the robot to track and mimic unseen human motions and further enables the robot to reuse the learned latent space for other tasks. We demonstrate the effectiveness of our framework through a diverse set of motions and accurate execution.

Heyuan Yao, Willow Kowalik, Izzy Grosof

Modern computing systems process jobs with resource requirements such as CPU and memory, which are described by multiresource jobs (MRJ) queueing models. In practice, job resource requirements are spread out over so many values, that it is rare to see the same value twice. This pattern is best modeled by a continuous distribution of requirement values. However, the existing theoretical work on stability or throughput-optimality focuses on queueing models with class-based resource requirements. In class-based models, the number of distinct resource requirements must be small to demonstrate strong empirical performance, making them a poor match for these practical systems. We introduce the first throughput-optimal family of scheduling policies for the continuous MRJ model, with both preemptive and nonpreemptive variants. We further introduce several efficient policy families, which remain throughput-optimal while considerably improving computational efficiency, under some distributional assumptions. We use a discretization approach, where we choose the discretization granularity based on the system load and the distribution of resource requirements. We validate the real-world applicability of our policies by comparing them against existing index-based policies on parametrized distributions and on datacenter trace data from the Google Borg scheduler, demonstrating state-of-the-art performance.

Weihao Tan, Xiangyang Li, Yunhao Fang et al.

We introduce Lumine, the first open recipe for developing generalist agents capable of completing hours-long complex missions in real time within challenging 3D open-world environments. Lumine adopts a human-like interaction paradigm that unifies perception, reasoning, and action in an end-to-end manner, powered by a vision-language model. It processes raw pixels at 5 Hz to produce precise 30 Hz keyboard-mouse actions and adaptively invokes reasoning only when necessary. Trained in Genshin Impact, Lumine successfully completes the entire five-hour Mondstadt main storyline on par with human-level efficiency and follows natural language instructions to perform a broad spectrum of tasks in both 3D open-world exploration and 2D GUI manipulation across collection, combat, puzzle-solving, and NPC interaction. In addition to its in-domain performance, Lumine demonstrates strong zero-shot cross-game generalization. Without any fine-tuning, it accomplishes 100-minute missions in Wuthering Waves and the full five-hour first chapter of Honkai: Star Rail. These promising results highlight Lumine's effectiveness across distinct worlds and interaction dynamics, marking a concrete step toward generalist agents in open-ended environments.

Zihao Wang, Xujing Li, Yining Ye et al. · pku

We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned native keyboard-mouse inputs. Unlike API- or GUI-based approaches, this paradigm enables large-scale continual pre-training across heterogeneous domains, including OS, web, and simulation games. Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data. Key techniques include a decaying continual loss to reduce causal confusion and an efficient Sparse-Thinking strategy that balances reasoning depth and inference cost. Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks, is close to the generality of fresh humans in unseen web 3d games, and outperforms GPT-5, Gemini-2.5-Pro, and Claude-4-Sonnet in FPS benchmarks. Scaling results on training-time and test-time confirm that the unified action space sustains improvements when scaled to cross-game and multimodal data. Our results demonstrate that simple, scalable action representations combined with large-scale pre-training provide a promising path toward generalist agents with broad computer-use abilities.

Zeyi Zhang, Yanju Zhou, Heyuan Yao et al.

We present Social Agent, a novel framework for synthesizing realistic and contextually appropriate co-speech nonverbal behaviors in dyadic conversations. In this framework, we develop an agentic system driven by a Large Language Model (LLM) to direct the conversation flow and determine appropriate interactive behaviors for both participants. Additionally, we propose a novel dual-person gesture generation model based on an auto-regressive diffusion model, which synthesizes coordinated motions from speech signals. The output of the agentic system is translated into high-level guidance for the gesture generator, resulting in realistic movement at both the behavioral and motion levels. Furthermore, the agentic system periodically examines the movements of interlocutors and infers their intentions, forming a continuous feedback loop that enables dynamic and responsive interactions between the two participants. User studies and quantitative evaluations show that our model significantly improves the quality of dyadic interactions, producing natural, synchronized nonverbal behaviors.