Ke Wang

Is Memorization Actually Necessary for Generalization

InvBench: Can LLMs Accelerate Program Verification with Invariant Synthesis?

SuperCoder: Assembly Program Superoptimization with Large Language Models

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis

Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces

MAGE: Leveraging LLMs for Automated Mapper Generation in Parallel Programming

Back to Fundamentals: Re-Examining Memorization in Deep Learning Models

Is Memorization Actually Necessary for Generalization?