Yewen Pu

13

Papers

160

Total Citations

Papers (13)

Hypothesis Search: Inductive Reasoning with Language Models

InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct

Amortizing Pragmatic Program Synthesis with Rankings

Compiler Auto-Vectorization with Imitation Learning

Program Synthesis with Pragmatic Communication

Neurosymbolic Transformers for Multi-Agent Communication

Program Synthesis Guided Reinforcement Learning for Partially Observed Environments

Communicating Natural Programs to Humans and Machines

DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics

ANPL: Towards Natural Programming with Interactive Decomposition

Selecting Representative Examples for Program Synthesis

Verifiable Reinforcement Learning via Policy Extraction

Write, Execute, Assess: Program Synthesis with a REPL