Presentation

<
Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control
SessionPhysics-Based Human Characters
DescriptionMeet Diffuse-CLoC—a powerful unification of intuitive steering in kinematic motion generation and physics-based character control. By guiding diffusion over joint state-action spaces, it enables agile, steerable, and physically realistic motions across diverse downstream tasks—from obstacle avoidance to task-space control and motion in-betweening—all from a single model, with no fine-tuning required.
Authors
Xiaoyu Huang
University of California Berkeley
Robotics and AI Institute
Takara Truong
Stanford University
Robotics and AI Institute
Yunbo Zhang
Robotics and AI Institute
Fangzhou Yu
Robotics and AI Institute
Jean Pierre Sleiman
Robotics and AI Institute
Jessica Hodgins
Robotics and AI Institute
Koushil Sreenath
Robotics and AI Institute
University of California Berkeley
Farbod Farshidian
Robotics and AI Institute
Event Type
Technical Paper
TimeWednesday, 13 August 20254:45pm - 4:55pm PDT
LocationWest Building, Rooms 220-222
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Wednesday, 13 August 20253:45pm - 5:35pm PDTWest Building, Rooms 220-222
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationPhysics-Based Human Characters - Interactive Discussion
Similar Presentations
PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers
Motion Control via Metric-Aligning Motion Matching
PLT: Part-Wise Latent Tokens as Adaptable Motion Priors for Physically Simulated Characters