4 papers
LeRoPE: Learnable RoPE Frequencies Improve Language Modeling
Petros Karypis, Sean O'Brien, Shreyas Kadekodi +2
Rotary Positional Encodings (RoPE) are currently the most popular positional encodings used in modern language models. RoPE rotates two-dimensional chunks of query and key vectors,…
Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models
Julian Skirzynski, Harry Cheon, Shreyas Kadekodi +2
Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few data…
A Framework for the Systematic Evaluation of Obstacle Avoidance and Object-Aware Controllers
Caleb Escobedo, Nataliya Nechyporenko, Shreyas Kadekodi +1
Real-time control is an essential aspect of safe robot operation in the real world with dynamic objects. We present a framework for the analysis of object-aware controllers, method…
CAT-RRT: Motion Planning that Admits Contact One Link at a Time
Nataliya Nechyporenko, Caleb Escobedo, Shreyas Kadekodi +1
Current motion planning approaches rely on binary collision checking to evaluate the validity of a state and thereby dictate where the robot is allowed to move. This approach leave…