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
Does ‘Do Differentiable Simulators Give Better Policy Gradients?’ Give Better Policy Gradients?
Published in International Conference on Learning Representations (ICLR 2026), 2026
A study of gradient estimation in differentiable simulators, introducing lightweight estimator switching and practical variance control.
Download Paper
Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation
Published in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2027), 2026
A group-based reinforcement learning objective that improves target-mode coverage while maintaining image quality and text alignment.
Download Paper
AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation
Published in arXiv preprint, 2026
An automatic method for optimizing the executable harness around frozen image generation and reasoning models.
Download Paper