7 papers
MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts
Abhinav Jain, Xinyu Yao, Thomas Reps +1
Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive. While prior work has demonstrated the effectiveness of using doma…
On The Finetuning of MLIPs Through the Lens of Iterated Maps With BPTT
Evan Dramko, Yizhi Zhu, Aleksandar Krivokapic +4
Accurate structural relaxation is critical for advanced materials design. Traditional approaches built on physics-derived first-principles calculations are computationally expensiv…
ADAPT: Lightweight, Long-Range Machine Learning Force Fields Without Graphs
Evan Dramko, Yihuang Xiong, Yizhi Zhu +4
Point defects play a central role in driving the properties of materials. First-principles methods are widely used to compute defect energetics and structures, including at scale f…
Efficient Cost Bounds with Linear Maps
David M Kahn, Jan Hoffmann, Thomas Reps +1
The Automatic Amortized Resource Analysis (AARA) derives program-execution cost bounds using types. To do so, AARA often makes use of cost-free types, which are critical for the co…
Semantics of Sets of Programs
Jinwoo Kim, Shaan Nagy, Thomas Reps +1
Applications like program synthesis sometimes require proving that a property holds for all of the infinitely many programs described by a grammar - i.e., an inductively defined se…
Verifying Solutions to Semantics-Guided Synthesis Problems
Charlie Murphy, Keith Johnson, Thomas Reps +1
Semantics-Guided Synthesis (SemGuS) provides a framework to specify synthesis problems in a solver-agnostic and domain-agnostic way, by allowing a user to provide both the syntax a…