Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
portfolio
publications
Local 3D Editing via 3D Distillation of CLIP Knowledge
Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
PixelHuman: Animatable Neural Radiance Fields from Few Images
Published in arXiv preprint, 2023
Text2Control3D: Controllable 3D Avatar Generation in Neural Radiance Fields using Geometry-Guided Text-to-Image Diffusion Model
Published in arXiv preprint, 2023
FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields
Published in IEEE/CVF International Conference on Computer Vision (ICCV), 2023
MagiCapture: High-Resolution Multi-Concept Portrait Customization
Published in Association for the Advancement of Artificial Intelligence (AAAI), 2024
SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder
Published in 18th European Conference on Computer Vision (ECCV), 2024
Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting
Published in Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel-based Head Avatars
Published in Thirteenth International Conference on Learning Representations (ICLR), 2025
Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs
Published in 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models
Published in Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
ACG: Action Coherence Guidance for Flow-based VLA models
Published in IEEE International Conference on Robotics & Automation (ICRA), 2026
EgoX: Egocentric Video Generation from a Single Exocentric Video
Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Towards Data-Efficient and Real-Time World Models
Published in Under Review, 2026
A two-stage discrete diffusion-based approach to world modelling: replacing the next-token prediction paradigm with a lightweight refinement transformer that carries out iterative masked predictions. Achieves a 79x speed-up over an autoregressive world model with limited deterioration in output quality, and can be trained to reproduce high-quality, consistent gameplay from roughly one day (28 hours) of gameplay data.
Generative Failure-to-Success Bridging for Robot Learning
Published in Under Review, 2026
Geometry-Aware Mid-Training for World-Action Models
Published in Under Review, 2026
