10 papers
Automated Discovery Has No Universally Superior Harness
Akshat Gupta, Jermaine Lei, Alexander Lu +2
Autonomous discovery systems such as OpenEvolve and TTT-Discover are often used as general-purpose harnesses. However, in practice these are composite systems combining several des…
How Do LLMs Use Their Depth?
Akshat Gupta, Jay Yeung, Gopala Anumanchipalli +1
Growing evidence suggests that large language models do not use their depth uniformly, yet we still lack a fine-grained understanding of their layer-wise prediction dynamics. In th…
AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
Mert Cemri, Shubham Agrawal, Akshat Gupta +9
The paradigm of automated program generation is shifting from one-shot generation to inference-time search, where Large Language Models (LLMs) function as semantic mutation operato…
Evolutionary Strategies lead to Catastrophic Forgetting in LLMs
Immanuel Abdi, Akshat Gupta, Micah Mok +3
One of the biggest missing capabilities in current AI systems is the ability to learn continuously after deployment. Implementing such continually learning systems have several cha…
BOA Constrictor: A Mamba-based lossless compressor for High Energy Physics data
Akshat Gupta, Caterina Doglioni, Thomas Joseph Elliott
The petabyte-scale data generated annually by High Energy Physics (HEP) experiments like those at the Large Hadron Collider present a significant data storage challenge. Whilst tra…
The Oracle Has Spoken: A Multi-Aspect Evaluation of Dialogue in Pythia
Zixun Chen, Petr Babkin, Akshat Gupta +2
Dialogue is one of the landmark abilities of large language models (LLMs). Despite its ubiquity, few studies actually distinguish specific ingredients underpinning dialogue behavio…