Cutting the Skip: Training Residual-Free Transformers
Abstract: Transformers are ubiquitous. They influence nearly every aspect of modern AI. However, the mechanics of their training remain poorly understood. This poses a problem for the field due to the immense amounts of data, computational power, and energy being invested in the training of these networks. I highlight a recent intriguing empirical result from [...]
Towards Smarter and Safer Self-Improving AI
Abstract: As AI systems become more capable, further progress may depend not only on scaling models and training data, but also on enabling systems to evaluate and improve their own behavior and development. This raises a dual challenge: how can we make self-improvement more effective while ensuring increasingly autonomous systems remain trustworthy? This thesis investigates [...]
Evaluating World Models in Embodied Question Answering through Computational Primitives and Difficulty Progressions
Abstract: Language modeling progress is largely evidenced by steadily rising scores on benchmarks of increasing apparent difficulty. From this, the field infers increasingly general capabilities, many of which presuppose robust world modeling. Interpreting a score, however, requires understanding both the task's computational requirements and how the test-taker generalizes from them. Unlike humans, who demonstrably generalize [...]
A Robotic System for Tree Nursery Automation
Abstract: The United States Green Industry faces a persistent labor shortage that motivates the adoption of agricultural automation. However, existing systems are not designed for the unstructured, densely planted environment of a tree nursery. This thesis presents a robotic system intended to alleviate this shortage while remaining usable by non-technical farmers, built around a [...]
[MS Thesis Talk] Terrain-Aware Dynamics Models for High-Speed Off-Road Navigation
Date: Tuesday, July 28, 2026 Time: 1:30pm- 2:30pm Location: GHC 9115 Title: Terrain-Aware Dynamics Models for High-Speed Off-Road Navigation Abstract: High-speed autonomy in the real world requires accurate control, which often relies on dynamics models that capture the complex interaction between a robot and its environment. In off-road regimes, this terrain interaction dominates the robot's dynamics, [...]
[MS Thesis Talk] Marble: An On-Manifold Approach to Solving Mathematical Programs with Complementarity Constraints
Date: Thursday, July 30, 2026 Time: 3:30 PM - 4:30 PM Location / ZOOM Link: (GHC 6115 / https://cmu.zoom.us/j/96096959582 ) Abstract: Many problems in robotics require reasoning over a mix of continuous dynamics and discrete events, such as making and breaking contact in manipulation and locomotion. These problems are locally well modeled by quadratic programs [...]